© 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. 57937
    Prev
    Next
    INDEX
    Explanations

    differential equations

    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
    uhi
    -0.09
    juta
    -0.09
    wein
    -0.08
    ä¸ĢåŃĹ
    -0.08
     Piem
    -0.08
    è£Ļ
    -0.08
    )::
    -0.08
     ("<
    -0.08
    TableRow
    -0.08
    idora
    -0.08
    POSITIVE LOGITS
    ...
    0.07
     +
    0.07
    en
    0.06
    inary
    0.06
    s
    0.06
     man
    0.06
    it
    0.06
    á
    0.06
     fib
    0.06
    +
    0.06
    Activations Density 0.003%

    No Known Activations