© 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. 80516
    Prev
    Next
    INDEX
    Explanations

    by

    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
     pode
    -0.06
    ..↵
    -0.06
    ﰲ
    -0.06
    might
    -0.06
     δ
    -0.06
    פשוט
    -0.06
    ')}}↵
    -0.06
     stars
    -0.06
     proteins
    -0.06
    `↵↵
    -0.06
    POSITIVE LOGITS
    -normal
    0.08
    写字
    0.07
    样子
    0.07
     booming
    0.07
    毛巾
    0.07
    倡
    0.07
    卜
    0.07
     charset
    0.06
    -reference
    0.06
    станав
    0.06
    Activations Density 0.005%

    No Known Activations