© 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. 48991
    Prev
    Next
    INDEX
    Explanations

    quotation marks with following content

    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
     nämlich
    -0.09
    åŃIJæĽ°
    -0.08
     totiž
    -0.08
    ieber
    -0.08
     ugyanis
    -0.07
    otka
    -0.07
    ÛĮع
    -0.07
    ivin
    -0.07
    uster
    -0.07
     übrigens
    -0.07
    POSITIVE LOGITS
    arne
    0.07
    让广大
    0.06
    urop
    0.06
    anken
    0.06
    .TryParse
    0.06
    ×ķת
    0.06
    esy
    0.06
    uges
    0.06
    [][
    0.06
    á»įt
    0.06
    Activations Density 0.057%

    No Known Activations