© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30401
    Prev
    Next
    INDEX
    Explanations

    technical figures and components

    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
    èį¡èį¡
    -0.07
    ãĤıãģij
    -0.07
    åĽ½å®¶æ£®æŀĹåħ¬åĽŃ
    -0.06
    URITY
    -0.06
    ectu
    -0.06
    lag
    -0.06
    åįģç«ł
    -0.06
    untos
    -0.06
    [class
    -0.06
    alsy
    -0.06
    POSITIVE LOGITS
    <|box_end|>
    0.08
    elsing
    0.07
     Bayer
    0.07
    å¾Ĺ天
    0.07
    天åĴĮ
    0.07
    зад
    0.07
    ukan
    0.07
    abad
    0.07
    ÑģÑģ
    0.07
    sWith
    0.07
    Activations Density 0.017%

    No Known Activations