© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 45481
    Prev
    Next
    INDEX
    Explanations

    burning, dissolving, charring, lathering

    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
    enties
    -0.08
    omma
    -0.07
    ÙĪØ·
    -0.07
    apé
    -0.06
    表éĿ¢ä¸Ĭ
    -0.06
    æѤåĪ»
    -0.06
    æļĤ
    -0.06
    azzi
    -0.06
    å°±è¿ij
    -0.06
    opak
    -0.06
    POSITIVE LOGITS
     easily
    0.11
     readily
    0.11
    è¿ħéĢŁ
    0.09
     quickly
    0.09
    ä¹Łå®¹æĺĵ
    0.09
     ÅĤatwo
    0.09
    à¸ĩà¹Īาย
    0.09
     facilement
    0.09
     fácilmente
    0.09
    _when
    0.09
    Activations Density 0.166%

    No Known Activations