© 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. 49842
    Prev
    Next
    INDEX
    Explanations

    sodium channels and currents

    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
    帼
    -0.08
    رد
    -0.08
    arton
    -0.08
    iette
    -0.07
    å½Ĵæ¯į
    -0.07
    é£ĺèį¡
    -0.07
    usband
    -0.07
    å®ŀç¼´
    -0.07
    ÑĢÑĥм
    -0.07
    åĤį
    -0.07
    POSITIVE LOGITS
    -rich
    0.07
    _INLINE
    0.07
    çĮ
    0.07
    дÑı
    0.07
    Fcn
    0.07
    çł´
    0.06
    ardin
    0.06
    èĻ
    0.06
    éĿŀ常快
    0.06
    ãģłãĤī
    0.06
    Activations Density 0.011%

    No Known Activations