© 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. 58708
    Prev
    Next
    INDEX
    Explanations

    jsfiddle links

    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
    åĪ©äºļ
    -0.07
    icke
    -0.07
    è¦ģæıIJé«ĺ
    -0.07
    å¨ĺ
    -0.07
    trut
    -0.06
    æĿİå°ı
    -0.06
    heimer
    -0.06
    quer
    -0.06
    ihan
    -0.06
    ä¹ı
    -0.06
    POSITIVE LOGITS
    ä½ķåľ¨
    0.07
    vs
    0.07
    iger
    0.07
    并请
    0.07
    丹éľŀ
    0.07
    æijĨäºĨ
    0.07
    ä½ķ
    0.07
    stamp
    0.07
    copy
    0.07
    ipc
    0.07
    Activations Density 0.050%

    No Known Activations