© 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. 42025
    Prev
    Next
    INDEX
    Explanations

    linear coefficients and constants

    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
    ASAN
    -0.08
    gow
    -0.07
    basename
    -0.07
    ahme
    -0.07
    {@
    -0.07
    ä½
    -0.07
     digest
    -0.07
    Pages
    -0.07
    æį¡
    -0.07
    blings
    -0.07
    POSITIVE LOGITS
     coefficients
    0.09
    coeff
    0.08
    Coeff
    0.08
     constants
    0.08
    .dependencies
    0.08
    etus
    0.07
     коÑįÑĦÑĦиÑĨи
    0.07
    linear
    0.07
    ç³»æķ°
    0.07
    æŶæĬ¥
    0.07
    Activations Density 0.097%

    No Known Activations