© 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. 62071
    Prev
    Next
    INDEX
    Explanations

    shapes and arrangements

    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
    itom
    -0.08
    ummer
    -0.07
    ä¹ĭéŨ
    -0.07
    /proto
    -0.07
    akan
    -0.07
    åľŁçŁ³
    -0.07
    æĿ¥çļĦ
    -0.07
    stones
    -0.07
     Cao
    -0.07
     خاک
    -0.07
    POSITIVE LOGITS
    æĸ¹ä¾¿
    0.08
    iteln
    0.07
    æ¶ķ
    0.07
    _distribution
    0.06
    agno
    0.06
     or
    0.06
    retti
    0.06
     circul
    0.06
     cess
    0.06
    ##_
    0.06
    Activations Density 0.143%

    No Known Activations