© 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. 8207
    Prev
    Next
    INDEX
    Explanations

    portion of

    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
    è·ĥ
    -0.06
    ä¿
    -0.06
    æĹĹä¸ĭ
    -0.06
     among
    -0.06
     Found
    -0.06
     val
    -0.06
    /cs
    -0.06
     listed
    -0.06
    æĬĬæĪij们
    -0.06
    æŶåĪ»
    -0.06
    POSITIVE LOGITS
     portions
    0.14
    è¿Ļéĥ¨åĪĨ
    0.12
     areas
    0.12
     regions
    0.11
     portion
    0.11
     Portions
    0.11
     ÑĥÑĩаÑģÑĤки
    0.11
     parts
    0.11
    areas
    0.10
     area
    0.10
    Activations Density 0.147%

    No Known Activations