© 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. 59658
    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
    Negative Logits
    .Sn
    -0.07
    excerpt
    -0.07
     Dict
    -0.06
    申请人
    -0.06
    _main
    -0.06
    _REQUEST
    -0.06
     хот
    -0.06
     spoken
    -0.06
     sangat
    -0.06
     Instructions
    -0.06
    POSITIVE LOGITS
    Kar
    0.07
     Pol
    0.07
    تكامل
    0.07
     Amar
    0.06
    _fold
    0.06
    Feel
    0.06
     Fest
    0.06
    잃
    0.06
    lasting
    0.06
    コース
    0.06
    Activations Density 0.239%

    No Known Activations