© 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. 34574
    Prev
    Next
    INDEX
    Explanations

    package structure or license

    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
    ä¸įåĨ³
    -0.11
    ász
    -0.08
    Ù°
    -0.08
    ì±ħìĿĦ
    -0.08
    éħ¸éĴ¾
    -0.08
    setzung
    -0.08
    orks
    -0.08
    ksen
    -0.08
    abelle
    -0.08
    oker
    -0.08
    POSITIVE LOGITS
     nhiêu
    0.10
    严å®ŀ
    0.08
    edly
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    aus
    0.07
    ishment
    0.07
    ings
    0.07
    ı
    0.07
    mehr
    0.07
    à§įষ
    0.07
    Activations Density 0.106%

    No Known Activations