© 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. 33846
    Prev
    Next
    INDEX
    Explanations

    math, code, or specific words preceded by punctuation

    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
     nomb
    -0.07
     Torn
    -0.07
    æłijä¸ĬçļĦ
    -0.07
    ianto
    -0.07
    ä¸įå¿į
    -0.07
    omie
    -0.06
    ÑģÑĭл
    -0.06
     Apocalypse
    -0.06
     nominee
    -0.06
    Send
    -0.06
    POSITIVE LOGITS
    iran
    0.08
    æĮ¡
    0.08
     Leisure
    0.07
    åħ¨éĿ¢äºĨ解
    0.07
    åıĺéĢŁ
    0.07
    çĬ¶æĢģçļĦ
    0.07
    è²
    0.07
    ullan
    0.07
    cms
    0.07
    æĵĭ
    0.07
    Activations Density 0.002%

    No Known Activations