© 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. 18208
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers

    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
    ÑĢики
    -0.07
    ercise
    -0.06
    rato
    -0.06
    CELER
    -0.06
    accia
    -0.06
    voke
    -0.06
    avis
    -0.06
    -git
    -0.06
    attan
    -0.06
    ocy
    -0.06
    POSITIVE LOGITS
    goed
    0.08
    empre
    0.08
    gan
    0.08
    uyan
    0.08
     اÙĦدÙħÙĪÙĬØ©
    0.08
    icona
    0.07
    åIJįåī¯
    0.07
    gether
    0.07
    uwen
    0.07
    ech
    0.07
    Activations Density 0.161%

    No Known Activations