© 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. 15240
    Prev
    Next
    INDEX
    Explanations

    Share on other sites

    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
    volo
    -0.08
     sny
    -0.07
    .nih
    -0.07
    åı¨
    -0.07
    rapped
    -0.07
    orer
    -0.07
    ä¸ĭæīĭ
    -0.07
    rending
    -0.07
    	date
    -0.07
    NER
    -0.07
    POSITIVE LOGITS
    Ł
    0.07
    heimer
    0.07
    opsis
    0.07
    WithError
    0.07
    summary
    0.07
    度çļĦ
    0.06
    ¨
    0.06
    ASSE
    0.06
    dale
    0.06
    amarin
    0.06
    Activations Density 0.075%

    No Known Activations