© 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. 45614
    Prev
    Next
    INDEX
    Explanations

    anthracene, benz, dibenz

    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
    åŃĺ
    -0.08
    å¦Ĥ鼨
    -0.07
    ford
    -0.07
    é¦ĸä½į
    -0.07
    EEK
    -0.06
    åīįæİĴ
    -0.06
    .nasa
    -0.06
     Expo
    -0.06
    ery
    -0.06
    asti
    -0.06
    POSITIVE LOGITS
    æħij
    0.07
    à®°à®ļ
    0.07
    ingang
    0.07
     interactions
    0.07
    ENDOR
    0.07
    Pend
    0.07
    agam
    0.07
    atro
    0.07
    otros
    0.07
    -double
    0.07
    Activations Density 0.002%

    No Known Activations