© 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. 8985
    Prev
    Next
    INDEX
    Explanations

    coding questions, documentation, technical issues

    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
    erver
    -0.07
    é£İè¡Į
    -0.07
    òng
    -0.07
    åIJĮæĹ¥
    -0.07
    æĬ
    -0.07
    ingle
    -0.07
    gs
    -0.06
     Ñģобой
    -0.06
    ebut
    -0.06
    arto
    -0.06
    POSITIVE LOGITS
    0.08
     analyse
    0.07
    ä¹ĭæģĭ
    0.07
    ż
    0.07
    ez
    0.07
    cini
    0.07
     hereby
    0.07
     informations
    0.06
    ì¹Ļ
    0.06
    eret
    0.06
    Activations Density 0.058%

    No Known Activations