© 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. 11263
    Prev
    Next
    INDEX
    Explanations

    wound healing

    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
    èĤ¾çĹħ
    -0.08
     Saturn
    -0.08
    Sat
    -0.07
    íĮ
    -0.07
     terminator
    -0.07
    为äºĨ满足
    -0.07
     dodge
    -0.07
     Sat
    -0.07
     antic
    -0.07
    æŁ¥çľĭæĽ´å¤ļ
    -0.06
    POSITIVE LOGITS
    æĦĪåIJĪ
    0.17
     healing
    0.15
     Healing
    0.14
    伤åı£
    0.13
     heals
    0.11
    åĮħæīİ
    0.11
    åĤ·åı£
    0.11
     healed
    0.11
     wounds
    0.09
     wound
    0.09
    Activations Density 0.301%

    No Known Activations