© 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. 38397
    Prev
    Next
    INDEX
    Explanations

    Markov chain statistics

    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
    å¥Ĺ
    -0.08
    ocking
    -0.07
    anger
    -0.07
    adhan
    -0.07
    ostro
    -0.07
     applied
    -0.06
    endale
    -0.06
    座
    -0.06
    å¨ģåĬĽ
    -0.06
    (^
    -0.06
    POSITIVE LOGITS
    ä¸ĬçŃī
    0.07
     eksklus
    0.07
    PREC
    0.07
     statist
    0.07
    _FLASH
    0.07
    é£Ľãģ³
    0.07
    åIJ¦åĪĻ
    0.07
    embe
    0.07
    æļ´é¥®
    0.07
    èĮĥåĽ´åĨħ使çĶ¨
    0.07
    Activations Density 0.003%

    No Known Activations