© 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. 24334
    Prev
    Next
    INDEX
    Explanations

    expression, specify, declare

    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
    ullet
    -0.07
    resp
    -0.07
    称
    -0.07
    @brief
    -0.07
    ÄĽk
    -0.07
    aline
    -0.07
    åĢĴ
    -0.06
    walker
    -0.06
    velope
    -0.06
    声称
    -0.06
    POSITIVE LOGITS
    æĿ¥è¡¨è¾¾
    0.08
    表达æĸ¹å¼ı
    0.08
    çļĦ表达
    0.07
    æĿ¥è¡¨ç¤º
    0.07
    表达
    0.07
    表述
    0.07
    æľĢèµ·çłģ
    0.07
     appropriately
    0.07
    -lang
    0.07
     appropriate
    0.07
    Activations Density 0.027%

    No Known Activations