© 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. 47438
    Prev
    Next
    INDEX
    Explanations

    license version 3

    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
    vertise
    -0.07
     ezz
    -0.07
    Ñħе
    -0.07
    æ¶Īå¤±åľ¨
    -0.07
    nown
    -0.07
    aversable
    -0.07
    ELIT
    -0.07
     berin
    -0.07
     coro
    -0.07
    avicon
    -0.07
    POSITIVE LOGITS
    åıĬ以ä¸Ĭ
    0.07
    ush
    0.07
    uron
    0.07
     khuôn
    0.07
    amil
    0.07
    enn
    0.07
    æĪĸ以ä¸Ĭ
    0.06
    imo
    0.06
    âĦ¢
    0.06
    orz
    0.06
    Activations Density 0.405%

    No Known Activations