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. 48389
    Prev
    Next
    INDEX
    Explanations

    geo

    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
    癌症
    -0.07
    ﱭ
    -0.07
    ző
    -0.07
    ゼ
    -0.06
     Wel
    -0.06
    opi
    -0.06
     complexion
    -0.06
    emain
    -0.06
    Repositories
    -0.06
     Sok
    -0.06
    POSITIVE LOGITS
    yor
    0.07
    _CT
    0.07
    有效的
    0.07
    ????
    0.07
    Consumer
    0.07
    @[
    0.07
    _dates
    0.06
     graph
    0.06
    Snippet
    0.06
    imes
    0.06
    Activations Density 0.009%

    No Known Activations