© 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. 64638
    Prev
    Next
    INDEX
    Explanations

    biological and medical models

    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
    _dup
    -0.08
    -0.08
    èĬ±èIJ½
    -0.08
    enthe
    -0.08
    quoi
    -0.08
    å¸ĮæľĽåı¯ä»¥å¸®åĬ©
    -0.08
    å¦ĤæľīçĸijéĹ®
    -0.08
    noinspection
    -0.08
    Unhandled
    -0.07
    .websocket
    -0.07
    POSITIVE LOGITS
     modeled
    0.07
    èĢIJä¹ħ
    0.07
     stochastic
    0.07
     fraction
    0.07
    éļıæľº
    0.06
    â
    0.06
     доÑģÑĤÑĥпна
    0.06
    建模
    0.06
     probabil
    0.06
    åľ¨ä¸Ģå®ļ
    0.06
    Activations Density 0.060%

    No Known Activations