© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46561
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code formatting

    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
    eter
    -0.07
    urry
    -0.07
    æĢ»é¢Ŀ
    -0.07
    足çļĦ
    -0.06
    åĬłèµ·æĿ¥
    -0.06
    å·¥ä½ľä¸ĬçļĦ
    -0.06
    足äºĨ
    -0.06
    wing
    -0.06
    交代
    -0.06
    ITTER
    -0.06
    POSITIVE LOGITS
    uus
    0.08
    .which
    0.07
    ëģĶ
    0.07
    ónimo
    0.07
    rezz
    0.07
    emus
    0.07
    .none
    0.06
    èĪĴçķħ
    0.06
    .animation
    0.06
    utch
    0.06
    Activations Density 0.003%

    No Known Activations