© 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. 31720
    Prev
    Next
    INDEX
    Explanations

    amide, linkage, cloth, saturated, medium, granul

    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
    omics
    -0.08
    å±ł
    -0.07
    lectic
    -0.06
    ocen
    -0.06
    æIJģ
    -0.06
    çĶµæ°Ķå·¥ç¨ĭ
    -0.06
     Chili
    -0.06
     باÙĦض
    -0.06
     garn
    -0.06
     sec
    -0.06
    POSITIVE LOGITS
    ä¸Ģ寸
    0.09
    ancier
    0.08
    寸
    0.07
    edd
    0.07
    uva
    0.07
    ERV
    0.07
    Åijd
    0.07
    æĸ¹ãĤĦ
    0.07
    æĪĸåħ¶å®ĥ
    0.07
    +</
    0.07
    Activations Density 0.015%

    No Known Activations