© 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. 32675
    Prev
    Next
    INDEX
    Explanations

    metric and metrics

    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
    heits
    -0.09
    idos
    -0.08
    heit
    -0.08
    holds
    -0.08
    itioner
    -0.08
    ////////////////////////////////////////////////
    -0.08
    گاÙĩ
    -0.08
    entifier
    -0.07
    MENTS
    -0.07
    elling
    -0.07
    POSITIVE LOGITS
    ally
    0.12
    ALLY
    0.09
    amente
    0.08
    ãĥ£ãĥ³
    0.08
    ually
    0.08
    ic
    0.08
    apolis
    0.08
    urgi
    0.08
    ä¸Ĭ说
    0.08
    дже
    0.08
    Activations Density 0.011%

    No Known Activations