© 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. 34601
    Prev
    Next
    INDEX
    Explanations

    "continue"

    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
    ấp
    -0.08
    è¯ķè¯ķ
    -0.08
    [value
    -0.07
    æĤ²æ¬¢
    -0.07
    两项
    -0.07
    ç¡®
    -0.07
    azit
    -0.07
    é¦ĸä¾ĭ
    -0.07
    èļ£
    -0.07
    è¯ķè¯ķçľĭ
    -0.07
    POSITIVE LOGITS
    æ·±åħ¥
    0.09
    lett
    0.07
    اÛĮت
    0.07
    æ¹Ľ
    0.07
    INTERNAL
    0.07
    ç²¹
    0.07
    ptrdiff
    0.07
    unis
    0.07
     elabor
    0.07
    çı
    0.07
    Activations Density 0.019%

    No Known Activations