© 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. 51979
    Prev
    Next
    INDEX
    Explanations

    max-len, max-statements, overflow, break, depth

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    rael
    -0.09
     fordel
    -0.08
    缩影
    -0.07
    yim
    -0.07
    ãģŀ
    -0.07
    mouseenter
    -0.07
    å½±åŃIJ
    -0.07
    ¬ģ
    -0.07
    åķ¡
    -0.07
    orea
    -0.06
    POSITIVE LOGITS
    æł¼å°Ķ
    0.07
    arith
    0.06
    çĸ½
    0.06
    ï¸İ
    0.06
     recursion
    0.06
    udy
    0.06
    edel
    0.06
    èĬ®
    0.06
    eph
    0.06
    åŁł
    0.06
    Activations Density 0.001%

    No Known Activations