© 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. 25646
    Prev
    Next
    INDEX
    Explanations

    regression coefficients and weights

    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
    ×Ļר×ķ
    -0.08
    è
    -0.08
    èŁĨ
    -0.07
    è½®åĪ°
    -0.07
    æ³³
    -0.07
    ACES
    -0.07
     Gregg
    -0.07
    å§Ĺ
    -0.07
    ÑĮми
    -0.07
    odable
    -0.06
    POSITIVE LOGITS
     coefficients
    0.09
    åĢ¼æѤ
    0.08
    Coeff
    0.08
     mengajar
    0.07
    æĭŁåIJĪ
    0.07
    coef
    0.07
    åĴĮæī§è¡Į
    0.07
    elius
    0.07
    atan
    0.07
     coeff
    0.07
    Activations Density 0.013%

    No Known Activations