© 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. 13089
    Prev
    Next
    INDEX
    Explanations

    round cell sarcomareceptor potentiallock icontissue plasminogenarea under

    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
    ä¸įåħ¥
    -0.08
    ekom
    -0.08
    æŁ¥çľĭåħ¨éĥ¨
    -0.08
    chnik
    -0.07
    å®Įåħ¨åı¯ä»¥
    -0.07
    agnes
    -0.07
    ä¸ĢçĽ´ä»¥
    -0.07
    å·²è¿Ľåħ¥
    -0.07
    人åĿĩåı¯
    -0.07
    oleon
    -0.07
    POSITIVE LOGITS
    usu
    0.07
    ...).
    0.07
    ynt
    0.06
    æŶæīĢ
    0.06
    istine
    0.06
    çĶºãģ®
    0.06
    ³
    0.06
     Mai
    0.06
    ntl
    0.06
     certain
    0.06
    Activations Density 0.296%

    No Known Activations