© 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. 63404
    Prev
    Next
    INDEX
    Explanations

    sweat and sweating

    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
    endis
    -0.09
    ặng
    -0.09
    ¶
    -0.08
    ramid
    -0.08
    éron
    -0.08
    azin
    -0.08
    гаÑĤ
    -0.08
    deaux
    -0.08
    glied
    -0.08
    räder
    -0.08
    POSITIVE LOGITS
    åĩºæ±Ĺ
    0.12
    æ·ĭæ¼ĵ
    0.11
    æ±Ĺ
    0.11
    大æ±Ĺ
    0.10
    æ±Ĺæ°´
    0.08
    津津
    0.08
     sweat
    0.08
     sud
    0.08
    shirt
    0.07
    æ¯ĽåŃĶ
    0.07
    Activations Density 0.006%

    No Known Activations