© 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. 59131
    Prev
    Next
    INDEX
    Explanations

    descriptions after certain phrases

    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
    å·¥ç¨ĭå¸ĪæĭĽèģĺ
    -0.09
    sem
    -0.08
    afx
    -0.07
    潦
    -0.07
    sembly
    -0.07
    åıĪæĬĬ
    -0.07
    ÙħÛĮÙĨ
    -0.07
    Äıte
    -0.07
    ldb
    -0.07
    ×Ļ׳×ķ
    -0.07
    POSITIVE LOGITS
    æĥŃ
    0.07
    gw
    0.07
    ITED
    0.06
    पà¥įत
    0.06
    go
    0.06
    å±ħ
    0.06
    EV
    0.06
    å¨ĩ
    0.06
    ä¸ĢåŃĹ
    0.06
    _VOID
    0.06
    Activations Density 0.004%

    No Known Activations