© 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. 19449
    Prev
    Next
    INDEX
    Explanations

    fractional notation

    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
    aka
    -0.07
     keen
    -0.06
    azo
    -0.06
    ways
    -0.06
    ican
    -0.06
    illen
    -0.06
    cke
    -0.06
     ((
    -0.06
    ذج
    -0.06
    man
    -0.06
    POSITIVE LOGITS
    деÑģÑı
    0.08
    æĪijæĿ¥è¯´
    0.08
    ÙĬØ«
    0.08
    amespace
    0.08
    िता
    0.07
    fuse
    0.07
    TimeString
    0.07
    æĿ¥æºIJäºİç½ij绾
    0.07
    .toBe
    0.07
    ķ
    0.07
    Activations Density 0.006%

    No Known Activations