© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 5676
    Prev
    Next
    INDEX
    Explanations

    Broadcast media excerpts

    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_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
    Negative Logits
    .equalsIgnoreCase
    -0.07
     cps
    -0.07
    仅次
    -0.07
     bourbon
    -0.07
     condominium
    -0.07
    .StackTrace
    -0.06
    yu
    -0.06
     File
    -0.06
     hauling
    -0.06
    𝘸
    -0.06
    POSITIVE LOGITS
    actice
    0.07
    keletal
    0.07
     информации
    0.07
    Ax
    0.07
    ateg
    0.07
    ач
    0.07
    (li
    0.07
    救
    0.07
    \)
    0.07
     Plastic
    0.07
    Activations Density 0.013%

    No Known Activations