© 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. 56416
    Prev
    Next
    INDEX
    Explanations

    biological process

    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
    åį«ä¸ľ
    -0.09
    ä¸½å¨ľ
    -0.08
     rotated
    -0.07
    à´ķàµįà´ķà´¾
    -0.07
    使çĶ¨æŶ
    -0.07
    ovable
    -0.07
    .callback
    -0.07
    åĩºæĪĺ
    -0.07
    使çĶ¨æĥħåĨµ
    -0.07
     matchup
    -0.07
    POSITIVE LOGITS
    è¿Ļ个è¿ĩç¨ĭ
    0.19
    è¿ĩç¨ĭ
    0.19
     process
    0.17
    è¿ĩç¨ĭçļĦ
    0.16
    çļĦè¿ĩç¨ĭ
    0.16
    åıijçĶŁåľ¨
    0.16
     processes
    0.16
    è¿ĩç¨ĭåĴĮ
    0.15
    process
    0.15
    éģİç¨ĭ
    0.14
    Activations Density 0.168%

    No Known Activations