© 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. 31305
    Prev
    Next
    INDEX
    Explanations

    problem-solving/improvements

    np_max-act · gemini-2.0-flash

    language expressing capability and positive outcomes, especially words about ability, possibility, advantages, and improvement.

    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
    練
    -0.08
    INESS
    -0.08
     preg
    -0.07
    盂
    -0.07
     équip
    -0.06
    'options
    -0.06
    庤
    -0.06
    ولات
    -0.06
    风扇
    -0.06
     RI
    -0.06
    POSITIVE LOGITS
     Volk
    0.07
     Goku
    0.07
     sic
    0.07
     nämlich
    0.06
    .recycle
    0.06
     Jail
    0.06
     Nike
    0.06
    him
    0.06
     Moreover
    0.06
    .Matchers
    0.06
    Activations Density 1.336%

    No Known Activations