© 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. 58870
    Prev
    Next
    INDEX
    Explanations

    group, Open, format, Monitor

    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
    ä¸įæ¸ħ
    -0.07
    ä¸ĢæıIJ
    -0.07
    ATCH
    -0.06
    æ°¸è¿ľä¸įä¼ļ
    -0.06
    éģ¥
    -0.06
    ocol
    -0.06
    æĵ¦äº®
    -0.06
    à¹Īวม
    -0.06
     Dirty
    -0.06
    atch
    -0.06
    POSITIVE LOGITS
    _agents
    0.08
    æ²»å®ī
    0.08
    pun
    0.08
    InOut
    0.08
    seed
    0.07
     tecnic
    0.07
    ذب
    0.07
     pauta
    0.07
    _decay
    0.07
    [test
    0.07
    Activations Density 0.003%

    No Known Activations