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. 59488
    Prev
    Next
    INDEX
    Explanations

    Code/Data fragments

    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
     manner
    -0.07
    ︽
    -0.07
     mieux
    -0.07
    深切
    -0.07
     khoá
    -0.06
    投資
    -0.06
     paused
    -0.06
    �체
    -0.06
     pace
    -0.06
    ($
    -0.06
    POSITIVE LOGITS
     Girlfriend
    0.08
     {(
    0.07
     testimonials
    0.07
     MD
    0.07
     Rodrig
    0.07
    حم
    0.07
    -----
    0.07
    .getFirst
    0.07
    酋
    0.07
     possui
    0.07
    Activations Density 15.117%

    No Known Activations