© 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. 55650
    Prev
    Next
    INDEX
    Explanations

    running sum and reduce operations

    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
    奶
    -0.08
    utter
    -0.07
    omba
    -0.07
    amah
    -0.07
    ilah
    -0.07
    jú
    -0.07
    boxed
    -0.07
    åĪĢåŃIJ
    -0.07
    èĩ¼
    -0.07
    ymi
    -0.07
    POSITIVE LOGITS
    endance
    0.08
    ä»İå·¦
    0.07
    é¢Ĥ
    0.06
    acob
    0.06
    éĢĴ
    0.06
    ulk
    0.06
    äºijå³°
    0.06
    ס×Ļ×Ŀ
    0.06
    ëĪĦ
    0.06
     Dunk
    0.06
    Activations Density 0.004%

    No Known Activations