© 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. 34890
    Prev
    Next
    INDEX
    Explanations

    list items or structured data

    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
    éĢĨ天
    -0.06
    çľ¼çľĭ
    -0.06
    é¼ĵåĬ±åĴĮ
    -0.06
    igar
    -0.06
    /T
    -0.06
     Plumbing
    -0.06
    两çĶ¨
    -0.06
    inder
    -0.06
    argas
    -0.06
    azol
    -0.06
    POSITIVE LOGITS
    æ¯Ķäºļ
    0.08
     REFERENCES
    0.07
    loud
    0.07
    å±±é«ĺ
    0.07
    tro
    0.07
    None
    0.07
    vio
    0.07
    ÏĢÏī
    0.07
    hib
    0.07
    _timezone
    0.07
    Activations Density 0.006%

    No Known Activations