© 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. 81538
    Prev
    Next
    INDEX
    Explanations

    tuberculosis

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Bri
    -0.07
     ramifications
    -0.07
     Lam
    -0.07
     dashed
    -0.07
    _walk
    -0.07
     lee
    -0.07
    Ỷ
    -0.07
    𪩘
    -0.07
     Raf
    -0.06
    分流
    -0.06
    POSITIVE LOGITS
    أور
    0.07
    orianCalendar
    0.07
     Mour
    0.07
    貸款
    0.06
     Detective
    0.06
     surgery
    0.06
    uesta
    0.06
    斯特
    0.06
    .*;↵
    0.06
    เอ
    0.06
    Activations Density 0.002%

    No Known Activations