© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 61088
    Prev
    Next
    INDEX
    Explanations

    structured processes

    np_max-act · gemini-2.0-flash

    a special control token that marks conversation/message boundaries (system/role delimiters).

    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_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
    u
    -0.07
     hail
    -0.07
    ناق
    -0.07
     imag
    -0.06
     lame
    -0.06
    🤧
    -0.06
    ṯ
    -0.06
     carnival
    -0.06
     праздник
    -0.06
     dank
    -0.06
    POSITIVE LOGITS
     Character
    0.07
    펫
    0.07
    object
    0.07
    这一点
    0.07
    将其
    0.07
    降低
    0.07
     Account
    0.07
    aside
    0.07
    .Entry
    0.07
     sotto
    0.07
    Activations Density 0.028%

    No Known Activations