© 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. 40637
    Prev
    Next
    INDEX
    Explanations

    measure space and distribution

    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
    sbin
    -0.08
    ÐĹе
    -0.08
    Ñģанд
    -0.07
    *@
    -0.07
    znÄĽ
    -0.07
    ÙĬب
    -0.07
    æĭIJ
    -0.06
    OOK
    -0.06
    oui
    -0.06
    INAN
    -0.06
    POSITIVE LOGITS
    ga
    0.07
    رÙĬØ©
    0.07
    irk
    0.06
    ullo
    0.06
    ops
    0.06
    aur
    0.06
     ÐĴоÑģ
    0.06
    weighted
    0.06
    ponsored
    0.06
    认为æĺ¯
    0.06
    Activations Density 0.005%

    No Known Activations