© 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. 18891
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and code

    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
    æīĵåħ¥
    -0.07
    è¡Ĺæĭį
    -0.07
    lsi
    -0.07
     dep
    -0.07
     cosi
    -0.06
    æ¯Ķäºļ
    -0.06
    коÑģ
    -0.06
    ĥĿ
    -0.06
     urgently
    -0.06
    inarie
    -0.06
    POSITIVE LOGITS
    iefer
    0.07
    åĢŁæѤ
    0.07
    %E
    0.07
    éĹ°
    0.06
    jf
    0.06
    jte
    0.06
    æ§Ľ
    0.06
    (.)
    0.06
    æ¯ı天éĥ½
    0.06
    ä¼ģä¸ļè¦ģ
    0.06
    Activations Density 0.003%

    No Known Activations