© 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. 48969
    Prev
    Next
    INDEX
    Explanations

    cross-linked structures

    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
    æģ¯
    -0.08
    åĪ·å±ı
    -0.07
    ihin
    -0.07
    å¯IJ
    -0.07
     ÙħÙĨا
    -0.07
    æ±Ĥ人
    -0.07
    owi
    -0.07
    åį§
    -0.06
     αξιο
    -0.06
    abah
    -0.06
    POSITIVE LOGITS
    ç¦ģéĶ¢
    0.08
    /random
    0.08
    getc
    0.08
    plode
    0.08
    å¯Ĩ度
    0.07
    .Ptr
    0.07
    erox
    0.07
     structure
    0.07
    ç»ĵå®ŀ
    0.07
     density
    0.07
    Activations Density 0.011%

    No Known Activations