© 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. 19734
    Prev
    Next
    INDEX
    Explanations

    introduces specific entities or concepts

    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
     Prado
    -0.07
    ully
    -0.07
    embro
    -0.07
    ÙĪÙĬب
    -0.07
    engo
    -0.07
    brook
    -0.07
    æľīä»»ä½ķçĸijéĹ®
    -0.07
    rame
    -0.07
    кнÑĥÑĤÑĮ
    -0.07
    yme
    -0.07
    POSITIVE LOGITS
    æĩ¿
    0.07
    æ¹ĸåĮº
    0.07
    åѦéĩij
    0.06
    ao
    0.06
    俱
    0.06
    为éļ¾
    0.06
     Borgo
    0.06
    asia
    0.06
    åĪ©
    0.06
    å¾·åĭĴ
    0.06
    Activations Density 0.998%

    No Known Activations