© 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. 60286
    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
    Dispose
    -0.07
    eee
    -0.07
    像是
    -0.07
    Offline
    -0.07
    ↙
    -0.07
    就像是
    -0.07
    Invoice
    -0.07
    cid
    -0.07
    pkg
    -0.07
     CSRF
    -0.07
    POSITIVE LOGITS
    鳀
    0.08
     возмож
    0.07
     العدو
    0.07
    澭
    0.07
    于是我
    0.07
    垾
    0.07
     hilar
    0.07
     brink
    0.07
    [U
    0.06
     Territory
    0.06
    Activations Density 0.001%

    No Known Activations