© 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. 19351
    Prev
    Next
    INDEX
    Explanations

    PSS patient, brain mononucleosomes, glass fibers, LY-ar, transformed B

    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
    OrCreate
    -0.07
    ipel
    -0.07
    éĤ£åı¯
    -0.06
    大路
    -0.06
     Shiv
    -0.06
    indel
    -0.06
    ainte
    -0.06
    /star
    -0.06
    à¸ķà¸ģ
    -0.06
    ands
    -0.06
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.08
    -ci
    0.07
    çļĦåħ·ä½ĵæĥħåĨµ
    0.07
    è¯ī
    0.07
    èįīæł¹
    0.07
    ost
    0.07
    æľ¬æĿ¥æĺ¯
    0.07
    æ¯ķç«Łæĺ¯
    0.06
    ä¸ĢæľĿ
    0.06
    åįģä¸ĥç«ł
    0.06
    Activations Density 0.086%

    No Known Activations