© 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. 64039
    Prev
    Next
    INDEX
    Explanations

    contour integral

    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
    æŬ
    -0.07
     —
    -0.07
    离
    -0.06
     LLVM
    -0.06
    骡
    -0.06
    ira
    -0.06
     Scots
    -0.06
     spr
    -0.06
    计
    -0.06
    пÑĢа
    -0.06
    POSITIVE LOGITS
    dul
    0.09
     UMK
    0.09
    迦
    0.08
    ÄIJT
    0.08
    rapper
    0.08
     Kasat
    0.08
     Deadly
    0.08
    _OPCODE
    0.08
    epage
    0.08
    tud
    0.08
    Activations Density 0.004%

    No Known Activations