© 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. 13312
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No

    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
    chino
    -0.09
    umbo
    -0.08
    ional
    -0.08
    utam
    -0.08
    梢
    -0.07
    inser
    -0.07
    embe
    -0.07
    าà¸Ļุ
    -0.07
     sekedar
    -0.07
    ubat
    -0.06
    POSITIVE LOGITS
    thetic
    0.10
    atown
    0.09
    ftware
    0.09
    ept
    0.08
    indsight
    0.08
    othing
    0.08
    лÑĮзÑı
    0.08
    ittal
    0.08
    оеди
    0.08
    peare
    0.08
    Activations Density 0.394%

    No Known Activations