© 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. 40204
    Prev
    Next
    INDEX
    Explanations

    Fmoc and mTOR pathways

    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
    versions
    -0.07
    rics
    -0.06
    cks
    -0.06
    нами
    -0.06
    боÑĢÑĭ
    -0.06
    æĥħåĨµ
    -0.06
    ç´§å¼ł
    -0.06
    ãģ£ãģ·
    -0.06
    Âł
    -0.06
    лей
    -0.06
    POSITIVE LOGITS
    ske
    0.09
    _BUFF
    0.08
    atro
    0.08
    æĿ¥çĶµåĴ¨è¯¢
    0.07
     batchSize
    0.07
    ulangan
    0.07
    大ä¹ī
    0.07
    gül
    0.07
    azī
    0.07
    opus
    0.07
    Activations Density 0.024%

    No Known Activations