© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 13971
    Prev
    Next
    INDEX
    Explanations

    Phys. Rev. or Reviews

    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
    ủa
    -0.09
    opard
    -0.09
     espirit
    -0.09
    [href
    -0.09
    erness
    -0.08
    idades
    -0.08
    zeria
    -0.08
    á»ĵi
    -0.08
    æŶæį·
    -0.08
    uras
    -0.08
    POSITIVE LOGITS
    è°±
    0.06
    pectrum
    0.06
     spectrum
    0.06
     Insight
    0.06
    igr
    0.06
     Spectrum
    0.06
    iona
    0.06
     modeling
    0.06
    ç¡
    0.06
    IO
    0.06
    Activations Density 0.003%

    No Known Activations