Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 2413
    Prev
    Next
    INDEX
    Explanations

    it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (level
    -0.09
    خم
    -0.07
    [field
    -0.07
    —he
    -0.07
    margin
    -0.07
     Pitch
    -0.07
     Martin
    -0.07
    ミ
    -0.07
    Berlin
    -0.07
    ��
    -0.07
    POSITIVE LOGITS
    矫正
    0.07
    棽
    0.07
    .AddScoped
    0.07
    常用的
    0.07
    /ap
    0.07
    .u
    0.07
     openid
    0.06
    .DB
    0.06
    _success
    0.06
    弢
    0.06
    Activations Density 0.013%

    No Known Activations