© 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. 39964
    Prev
    Next
    INDEX
    Explanations

    knew or believable

    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
    ä¸ºæł¸å¿ĥçļĦ
    -0.08
     infinitely
    -0.07
    irth
    -0.07
     Hul
    -0.07
    æľīä¸īç§į
    -0.07
    ÑĦо
    -0.07
    iset
    -0.07
    æ·»
    -0.07
    对æĸ¹
    -0.07
    olla
    -0.06
    POSITIVE LOGITS
    åIJĪçIJĨæĢ§
    0.12
     reasonable
    0.10
    åIJĪçIJĨ
    0.10
    åIJĪçIJĨçļĦ
    0.10
     plausible
    0.09
    reasonable
    0.08
    ä¸įåIJĪçIJĨ
    0.08
     unreasonable
    0.08
    ä¸įèĩ³äºİ
    0.08
    åIJĪçIJĨåĮĸ
    0.08
    Activations Density 0.017%

    No Known Activations