© 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. 30791
    Prev
    Next
    INDEX
    Explanations

    spectrum physics or range

    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
    à¹Į
    -0.09
    aptor
    -0.08
    -regexp
    -0.08
    ãģĿãĤĮãģ§ãĤĤ
    -0.08
    ķ
    -0.08
     investid
    -0.08
    gäng
    -0.08
    HING
    -0.08
    entifier
    -0.08
    anca
    -0.08
    POSITIVE LOGITS
    -wide
    0.09
    æĹłéĺ»
    0.07
    窿
    0.07
    ansion
    0.07
    ingly
    0.07
    ption
    0.07
    æ³¢åĬ¨
    0.06
    resent
    0.06
     entirety
    0.06
    OfWork
    0.06
    Activations Density 0.017%

    No Known Activations