© 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. 9365
    Prev
    Next
    INDEX
    Explanations

    aspects and factors

    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
    baran
    -0.08
    bard
    -0.08
    -strokes
    -0.08
    áĥ©
    -0.08
    gak
    -0.08
    aeda
    -0.08
    ostro
    -0.08
    alais
    -0.08
    ivirus
    -0.08
    jukan
    -0.08
    POSITIVE LOGITS
    å±ĤéĿ¢çļĦ
    0.10
    å±ĤéĿ¢
    0.09
    -an
    0.07
    -
    0.07
    æĸ¹éĿ¢çļĦ
    0.07
    rical
    0.07
     counterpart
    0.07
    -a
    0.07
    /a
    0.07
     aspects
    0.06
    Activations Density 0.097%

    No Known Activations