© 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. 59596
    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
     Gra
    -0.07
    委
    -0.07
     vers
    -0.07
     Victorian
    -0.07
    ackson
    -0.07
    _Item
    -0.07
     organiz
    -0.06
    Harness
    -0.06
     furn
    -0.06
     Aval
    -0.06
    POSITIVE LOGITS
     reproduce
    0.07
    "><!--
    0.07
     tutti
    0.07
     Relatives
    0.07
    Usually
    0.06
    LIKELY
    0.06
     everlasting
    0.06
    UD
    0.06
     }}"><
    0.06
    据统计
    0.06
    Activations Density 0.015%

    No Known Activations