© 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. 31318
    Prev
    Next
    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    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
    person
    -0.07
    퍠
    -0.07
     drug
    -0.07
     recommending
    -0.07
     fins
    -0.07
     ting
    -0.07
    /msg
    -0.07
    ising
    -0.07
    𝘂
    -0.06
    Sure
    -0.06
    POSITIVE LOGITS
    比分
    0.08
    中国足球
    0.07
    ╍
    0.07
    🌊
    0.06
    PostalCodes
    0.06
    ▎
    0.06
    恒大
    0.06
    殖
    0.06
    ȍ
    0.06
    alary
    0.06
    Activations Density 0.002%

    No Known Activations