© 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. 49764
    Prev
    Next
    INDEX
    Explanations

    linear formulas and regressions

    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
    ikkel
    -0.07
    -generic
    -0.07
     пÑĥзÑĭÑĢÑı
    -0.07
    _compute
    -0.07
    è´´åIJĪ
    -0.07
    xAC
    -0.07
     (!((
    -0.07
    Spaces
    -0.07
    jep
    -0.07
    ibil
    -0.06
    POSITIVE LOGITS
     intercept
    0.10
     slope
    0.09
    æĪª
    0.09
     theoretically
    0.08
     Intercept
    0.08
    empre
    0.08
     fitted
    0.08
     constant
    0.08
    slope
    0.07
    ä¸ĩéĩĮ
    0.07
    Activations Density 0.002%

    No Known Activations