© 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. 10373
    Prev
    Next
    INDEX
    Explanations

    customer names or identifiers

    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
    GES
    -0.06
    ri
    -0.06
    LS
    -0.06
    ç»ĵäºĨ
    -0.06
    ingen
    -0.06
    åħ»çļĦ
    -0.06
    ä¾ĽåºĶ产åĵģ
    -0.06
    Ball
    -0.06
    FromArray
    -0.06
    ÏĦαν
    -0.06
    POSITIVE LOGITS
    ضÙĬ
    0.08
    æ¯Ķäºļ
    0.08
    YN
    0.08
    _eof
    0.08
    åĨĴ
    0.07
    Äijenje
    0.07
    envir
    0.07
    elines
    0.07
    ÙħÙĬÙħ
    0.07
    ezd
    0.07
    Activations Density 0.190%

    No Known Activations