© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52079
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    asso
    -0.08
    antt
    -0.07
    ua
    -0.07
    ardi
    -0.07
    üle
    -0.07
    koa
    -0.07
    ulty
    -0.07
    imb
    -0.07
    ç¾İæľ¯å®¶åįıä¼ļ
    -0.07
    коли
    -0.07
    POSITIVE LOGITS
    è·Ŀ
    0.09
     distance
    0.08
     distances
    0.08
    bris
    0.07
    standing
    0.07
    éģµä»İ
    0.07
    distance
    0.07
    istance
    0.07
    è·Ŀ离
    0.07
    Encoding
    0.07
    Activations Density 0.000%

    No Known Activations