© 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. 38459
    Prev
    Next
    INDEX
    Explanations

    sensory organs and senses

    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
    еÑĩа
    -0.08
     ellipt
    -0.08
    åij¨è½¬
    -0.07
    ÑĬÑİ
    -0.07
     Sput
    -0.07
     turnaround
    -0.07
    ToFit
    -0.07
    éĩijæĸ¯
    -0.07
    DateFormat
    -0.07
    ãĥķãĤ©ãĥŃãĥ¼
    -0.07
    POSITIVE LOGITS
     sensory
    0.16
    触è§ī
    0.15
     tactile
    0.14
     sensations
    0.13
    æĦŁçŁ¥
    0.13
    æĦŁå®ĺ
    0.13
     sensation
    0.12
     ÑģенÑģоÑĢ
    0.11
    ä¼łåħ¥
    0.11
     sensor
    0.11
    Activations Density 0.095%

    No Known Activations