© 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. 46888
    Prev
    Next
    INDEX
    Explanations

    following "in"

    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
    çĤİçĤİ
    -0.06
     darn
    -0.06
    æ®ĭçĸ¾
    -0.06
    ãģ³
    -0.06
    ä¸Ĭæľī
    -0.06
    ç»Ļ人ä¸Ģç§į
    -0.06
    itage
    -0.06
    porter
    -0.06
    mé
    -0.06
    ']="
    -0.06
    POSITIVE LOGITS
    人æĿ¥è¯´
    0.09
    çļĦ人æĿ¥è¯´
    0.08
    æĥħåĨµæĿ¥çľĭ
    0.08
    áĢ¾
    0.07
    ฯ
    0.07
    aka
    0.07
    ç§ijæĬĢåİħ
    0.07
    ëĬIJ
    0.07
    èĢĮè¨Ģ
    0.07
    çŁ¥ç½ij
    0.07
    Activations Density 0.020%

    No Known Activations