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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 44129
    Prev
    Next
    INDEX
    Explanations

    say letters or numbers

    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
    זרח
    -0.08
     בנושא
    -0.07
     לאורך
    -0.07
     развитие
    -0.07
    钌
    -0.07
     utan
    -0.07
    🤟
    -0.07
     نطاق
    -0.07
    麽
    -0.07
    획
    -0.07
    POSITIVE LOGITS
    .embedding
    0.08
    Either
    0.07
    Temporary
    0.07
     specified
    0.07
    …↵
    0.06
    _CUSTOM
    0.06
     Confeder
    0.06
     "
    ↵
    0.06
    riday
    0.06
    颢
    0.06
    Activations Density 0.006%

    No Known Activations