© 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. 44964
    Prev
    Next
    INDEX
    Explanations

    coefficients, rates, and ratios

    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
    CG
    -0.07
    uzion
    -0.07
    isert
    -0.07
    å»ºæł¡
    -0.06
     brute
    -0.06
    ocr
    -0.06
    prof
    -0.06
     Liberties
    -0.06
    没æľīæŶéĹ´
    -0.06
    沧
    -0.06
    POSITIVE LOGITS
     coefficient
    0.10
     rate
    0.08
    ç³»æķ°
    0.08
     elasticity
    0.08
     coefficients
    0.08
     slopes
    0.08
     slope
    0.08
     Rate
    0.08
    Coefficient
    0.08
     rates
    0.08
    Activations Density 0.019%

    No Known Activations