© 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. 65510
    Prev
    Next
    INDEX
    Explanations

    programming type declarations

    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
    /dev
    -0.08
    æĸ¹å¼ı使çĶ¨
    -0.07
    /res
    -0.07
     Roos
    -0.07
    /stretch
    -0.07
    <this
    -0.07
    ()."
    -0.07
    /re
    -0.07
     <!--<
    -0.07
    uden
    -0.07
    POSITIVE LOGITS
    |null
    0.07
     WINAPI
    0.07
    iki
    0.07
    aveur
    0.07
    assa
    0.07
    Nullable
    0.07
    bella
    0.06
    زÙĪ
    0.06
    opsy
    0.06
     keting
    0.06
    Activations Density 0.076%

    No Known Activations