© 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. 55158
    Prev
    Next
    INDEX
    Explanations

    relevant data are

    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
    è§Ħ
    -0.09
    ัà¸ļ
    -0.07
    krit
    -0.07
    å±ŀäºİ
    -0.06
    ore
    -0.06
    atto
    -0.06
    åºĦåĽŃ
    -0.06
    æŶèĢĮ
    -0.06
    agger
    -0.06
    opes
    -0.06
    POSITIVE LOGITS
    ä¸Ńèĭ±
    0.08
    </think>
    0.07
     accogli
    0.07
    翼翼
    0.07
     sworn
    0.07
    ÅĽc
    0.07
    çļĦä¸ĵæłı
    0.07
    /cgi
    0.07
    /kernel
    0.07
    æīĵéĽ»è©±
    0.07
    Activations Density 0.003%

    No Known Activations