© 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. 50516
    Prev
    Next
    INDEX
    Explanations

    observable behavior and expression

    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
    æ¿ĢæĪĺ
    -0.08
    æĽ¿å°¼
    -0.08
    å§ĵ
    -0.07
    umpang
    -0.07
    壮éĺĶ
    -0.07
    koa
    -0.07
     cita
    -0.07
     footh
    -0.07
    åľ¨ä»ĸ们çļĦ
    -0.07
    avax
    -0.07
    POSITIVE LOGITS
     behavior
    0.13
    è¡Į为
    0.13
    举æŃ¢
    0.13
     behaviors
    0.12
     behaviour
    0.12
     observable
    0.11
    behavior
    0.11
    è¡Į为åĴĮ
    0.11
     Behavior
    0.11
    è¡Į为çļĦ
    0.11
    Activations Density 0.057%

    No Known Activations