© 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. 38640
    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
    macher
    -0.08
    FromClass
    -0.07
    天边
    -0.07
    otov
    -0.07
    áĥĶáĥijáĥIJ
    -0.07
    üt
    -0.07
    家
    -0.07
     ana
    -0.07
    oyer
    -0.07
    幸ç¦ıçĶŁæ´»
    -0.07
    POSITIVE LOGITS
    iban
    0.07
    ffb
    0.07
    igue
    0.07
    à®´
    0.06
    æĿĢæīĭ
    0.06
     Dil
    0.06
    iral
    0.06
    agas
    0.06
     ga
    0.06
     Grosso
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.