© 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. 71593
    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
    ➰
    -0.08
     ceasefire
    -0.07
     هاتف
    -0.07
    ;}
    -0.07
     blinded
    -0.07
    מפקד
    -0.07
     meny
    -0.07
     Phase
    -0.07
     StartTime
    -0.07
     suites
    -0.07
    POSITIVE LOGITS
    /Public
    0.09
    景观
    0.08
    干部
    0.07
     booths
    0.07
     predictor
    0.07
    水平
    0.07
    _cart
    0.07
    社会保障
    0.07
     ?>><?
    0.06
    /tools
    0.06
    Activations Density 0.003%

    No Known Activations