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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 8985
    Prev
    Next
    INDEX
    Explanations

    period

    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
    تنظيف
    -0.07
    azor
    -0.06
    ภาย
    -0.06
    真假
    -0.06
    DFS
    -0.06
    ^\
    -0.06
    $smarty
    -0.06
    מייל
    -0.06
    (mask
    -0.06
    /problem
    -0.06
    POSITIVE LOGITS
    矗
    0.07
     Prot
    0.07
    _label
    0.07
    nton
    0.07
     propagation
    0.07
     Races
    0.07
    Escort
    0.06
     ................
    0.06
    ybrid
    0.06
     fot
    0.06
    Activations Density 0.061%

    No Known Activations