© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2683
    Prev
    Next
    INDEX
    Explanations

    fasting state

    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
    俱ä¹IJéĥ¨
    -0.08
    Ĺı
    -0.08
    outers
    -0.08
    å½ĵåĪĿ
    -0.07
     Année
    -0.07
    åĩ¹åĩ¸
    -0.07
    umn
    -0.07
    éĢIJå¹´
    -0.07
    æĪIJæ´»
    -0.07
    _PEER
    -0.07
    POSITIVE LOGITS
     fasting
    0.10
    空èħ¹
    0.09
     habitual
    0.08
    æķ°æį®éĩĩéĽĨ
    0.08
     voluntary
    0.07
    uke
    0.07
    éĩĩéĽĨ
    0.07
     tap
    0.07
    æĨĭ
    0.07
    routine
    0.07
    Activations Density 0.212%

    No Known Activations