© 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. 71601
    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
     中
    -0.07
    今
    -0.07
    cock
    -0.07
     village
    -0.06
    付
    -0.06
    коль
    -0.06
    	side
    -0.06
    เมน
    -0.06
     Flickr
    -0.06
    Portrait
    -0.06
    POSITIVE LOGITS
    _RANK
    0.08
    áz
    0.07
    [#
    0.07
    utar
    0.07
     Duel
    0.07
    .+
    0.07
     consulted
    0.06
    datos
    0.06
     ROT
    0.06
    זול
    0.06
    Activations Density 0.024%

    No Known Activations