© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 128776
    Prev
    Next
    INDEX
    Explanations

    _SIZE

    np_max-act · gemini-2.0-flash
    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
    🍦
    -0.07
    Confirm
    -0.07
     cowboy
    -0.07
    不少于
    -0.07
    .updated
    -0.07
     nud
    -0.07
    有趣的
    -0.07
    lemn
    -0.06
    компонент
    -0.06
    叕
    -0.06
    POSITIVE LOGITS
    以致
    0.07
    해야
    0.07
    actions
    0.07
     كيفية
    0.07
     Silence
    0.07
     presentation
    0.07
    حصول
    0.07
     für
    0.07
    ations
    0.07
    straction
    0.07
    Activations Density 0.002%

    No Known Activations