© 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. 40310
    Prev
    Next
    INDEX
    Explanations

    exp, semigroup, maximal, eigh

    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
    ł
    -0.08
    å¾Ģä¸ĭ
    -0.07
    awk
    -0.07
     Ayu
    -0.07
    RAW
    -0.07
     masked
    -0.07
    å¼ķãģ£
    -0.06
    è·¨åĽ½
    -0.06
    alon
    -0.06
    大åij¼
    -0.06
    POSITIVE LOGITS
     пÑĢоÑģп
    0.08
    åĪ¶èį¯
    0.08
     exponentially
    0.08
    yntax
    0.07
    æ¿ĢåħīåĻ¨
    0.07
    æ´¾çļĦ
    0.07
    olda
    0.07
    ணி
    0.07
    -operator
    0.07
    leigh
    0.07
    Activations Density 0.005%

    No Known Activations