© 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. 60453
    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
    (New
    -0.08
    Wrap
    -0.07
    .Equal
    -0.07
     wspóln
    -0.07
    叚
    -0.07
    -indent
    -0.06
     المجال
    -0.06
    做过
    -0.06
    西班
    -0.06
    .bg
    -0.06
    POSITIVE LOGITS
    ouv
    0.08
     )]↵
    0.06
     Ellie
    0.06
    ailand
    0.06
     Security
    0.06
    ))+
    0.06
    털
    0.06
     ולה
    0.06
    呼び
    0.06
    四
    0.06
    Activations Density 0.105%

    No Known Activations