© 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. 18181
    Prev
    Next
    INDEX
    Explanations

    isolated membrane patches

    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
    abia
    -0.08
     slog
    -0.08
    å®ļåŀĭ
    -0.07
    orter
    -0.07
    åĴĮç¾İ
    -0.07
    kak
    -0.07
    lsa
    -0.07
     haus
    -0.07
    meros
    -0.07
    amber
    -0.07
    POSITIVE LOGITS
    INCLUDE
    0.08
    è¿IJ
    0.08
     Pio
    0.07
    TERNAL
    0.07
    bene
    0.07
     isolation
    0.06
    çij¶
    0.06
     puol
    0.06
    _scope
    0.06
    ä¸Ģèµ·
    0.06
    Activations Density 0.003%

    No Known Activations