© 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. 51327
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éĿŀçī©è´¨
    -0.07
    ä¸Ģæĺ¯
    -0.07
    onium
    -0.06
    agoza
    -0.06
    wil
    -0.06
    yntax
    -0.06
    moni
    -0.06
    æ°´åĪĨ
    -0.06
    dn
    -0.06
    æĢ¥èºģ
    -0.06
    POSITIVE LOGITS
    ynch
    0.08
    onsense
    0.08
    ix
    0.07
    urette
    0.07
    ÑģÑĭ
    0.07
    IX
    0.07
    CSV
    0.07
     stdin
    0.07
    utable
    0.07
    exion
    0.07
    Activations Density 0.000%

    No Known Activations