© 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. 15-RESID-POST-AA
    11. 79666
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     paddle
    -0.08
     McConnell
    -0.08
     chor
    -0.07
    _IMM
    -0.07
     dolor
    -0.07
    _MO
    -0.07
     rhythm
    -0.07
    .asp
    -0.07
    ÜR
    -0.07
    ENE
    -0.07
    POSITIVE LOGITS
     Aleks
    0.07
     developments
    0.07
    剧院
    0.07
    ','=','
    0.06
    发行人
    0.06
    真实的
    0.06
    &action
    0.06
    aker
    0.06
    --[
    0.06
    与中国
    0.06
    Activations Density 0.029%

    No Known Activations