© 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. 15-RESID-POST-AA
    11. 49361
    Prev
    Next
    INDEX
    Explanations

    Informing

    np_max-act · gemini-2.0-flash

    Sentences or phrases that instruct or urge reporting to authorities, supervisors, or other official parties (e.g., "inform/notify/report" someone).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     objetos
    -0.07
    DataFrame
    -0.07
    アジア
    -0.07
    清华
    -0.07
     effectively
    -0.06
     resil
    -0.06
    avr
    -0.06
     �
    -0.06
    科幻
    -0.06
    од
    -0.06
    POSITIVE LOGITS
     buddy
    0.07
    过错
    0.07
    .take
    0.07
    听得
    0.07
    !</
    0.07
    礼貌
    0.07
     ליד
    0.07
    .joda
    0.07
    ◑
    0.07
    吃过
    0.07
    Activations Density 0.081%

    No Known Activations