© 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. 29463
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and symbols

    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
    éĩįçĤ¹æĺ¯
    -0.07
    æİĢèµ·
    -0.07
    çļĦéĤ£ç§į
    -0.07
    ieh
    -0.07
    ords
    -0.07
    ingan
    -0.07
    quier
    -0.06
     though
    -0.06
    enc
    -0.06
    igit
    -0.06
    POSITIVE LOGITS
    onel
    0.07
    epam
    0.07
    à°¦à±ģ
    0.07
    ector
    0.07
    noinspection
    0.07
    auen
    0.06
    ç£IJ
    0.06
    nese
    0.06
    amer
    0.06
    CKET
    0.06
    Activations Density 0.001%

    No Known Activations