© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65430
    Prev
    Next
    INDEX
    Explanations

    glorifying violence

    np_max-act · gemini-2.0-flash

    language that endorses, glorifies, or encourages violence, harm, or immoral/evil behavior.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0

    language that promotes, glorifies, or instructs on harmful, violent, or illegal behavior, including encouragement of others to cause suffering.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -kind
    -0.07
    ipelines
    -0.07
    等方面
    -0.07
    不准
    -0.07
    文明
    -0.07
    dashboard
    -0.07
    clair
    -0.07
     impressive
    -0.06
    爽
    -0.06
    (Number
    -0.06
    POSITIVE LOGITS
     OSError
    0.08
    袆
    0.07
     table
    0.07
    ,None
    0.07
     watches
    0.07
     pomi
    0.07
    panion
    0.06
    IMPORTANT
    0.06
    INS
    0.06
    𝒿
    0.06
    Activations Density 0.165%

    No Known Activations