© 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. 71792
    Prev
    Next
    INDEX
    Explanations

    interrogative user queries, especially sentences ending in a question mark and “how-it-works” style questions.

    oai_token-act-pair · gpt-5
    Triggered by @vetterc0
    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
    让人们
    -0.08
    Weapon
    -0.07
    aption
    -0.07
     wn
    -0.07
    ippines
    -0.07
     datatable
    -0.06
    reta
    -0.06
     Views
    -0.06
     Governments
    -0.06
     Ancient
    -0.06
    POSITIVE LOGITS
    shaft
    0.07
    .goods
    0.07
    睡觉
    0.07
     quotid
    0.06
    PECIAL
    0.06
     encountered
    0.06
     satisfactory
    0.06
    Hair
    0.06
    lıkl
    0.06
    (dot
    0.06
    Activations Density 0.183%

    No Known Activations