© 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. 45917
    Prev
    Next
    INDEX
    Explanations

    git pull upstream client

    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
    å¼Ĥä½į
    -0.08
    æĢ¯
    -0.07
    زÙħ
    -0.07
    åĩ«
    -0.07
    à¸Ńà¸ģ
    -0.07
    uduk
    -0.07
    woff
    -0.07
    IVEN
    -0.07
    æīĢæľīç«łèĬĤ
    -0.07
    ledged
    -0.07
    POSITIVE LOGITS
    æ»¡åľ°
    0.07
    rtype
    0.07
    igi
    0.07
    rich
    0.06
    ral
    0.06
    anguage
    0.06
     zach
    0.06
     quite
    0.06
    mot
    0.06
    èĤ¥
    0.06
    Activations Density 0.001%

    No Known Activations