© 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. 42674
    Prev
    Next
    INDEX
    Explanations

    article usage

    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
    angg
    -0.08
    åħ¨åijĺ
    -0.07
    ipt
    -0.07
    èĸª
    -0.07
    ihat
    -0.07
    æĿ¿ä¸Ĭ
    -0.07
    ahoo
    -0.07
    outh
    -0.07
    é±¼åĦ¿
    -0.07
    个人è¡Į为
    -0.07
    POSITIVE LOGITS
     unnamed
    0.08
    elok
    0.08
    Unnamed
    0.08
    æĬ¹
    0.07
     opport
    0.07
    hd
    0.07
    æĺ¨å¤ľ
    0.07
    /an
    0.06
    /the
    0.06
     vag
    0.06
    Activations Density 0.027%

    No Known Activations