© 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. 25083
    Prev
    Next
    INDEX
    Explanations

    numbers and letters

    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
    Not in Any Lists

    No Comments

    Negative Logits
    undene
    -0.07
    缴æİ¥æĪĸ
    -0.07
    ondre
    -0.06
    ywa
    -0.06
    æĥŃ
    -0.06
    èIJ½èIJ½
    -0.06
    zze
    -0.06
    JK
    -0.06
    çĻ¾å§ĵç½ij
    -0.06
    æ³£
    -0.06
    POSITIVE LOGITS
    bidden
    0.07
    书åIJ§
    0.07
    *)_
    0.07
     **‘
    0.07
    eway
    0.07
    è¿ŀèĥľ
    0.07
    太éĥİ
    0.07
    smith
    0.07
    itude
    0.07
    å¦ĤåĪĿ
    0.07
    Activations Density 0.551%

    No Known Activations