© 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. 38655
    Prev
    Next
    INDEX
    Explanations

    transition and transformation

    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
    anz
    -0.07
    ัà¸į
    -0.07
    elon
    -0.07
     improvised
    -0.07
    èĩªçĦ¶çķĮ
    -0.06
    áĥĶáĥ¡
    -0.06
    ëĭĽ
    -0.06
    ¾
    -0.06
    _manage
    -0.06
    amenta
    -0.06
    POSITIVE LOGITS
    è¿Ľç¨ĭä¸Ń
    0.15
    è¿ĩç¨ĭä¸Ń
    0.13
    è¿Ľç¨ĭ
    0.12
    éģİç¨ĭä¸Ń
    0.11
    è¿ĩç¨ĭä¸ŃçļĦ
    0.11
    è¿Ļ个è¿ĩç¨ĭ
    0.11
    转åŀĭ
    0.11
    è¿Ľç¨ĭçļĦ
    0.11
     ê³¼ìłķìĹIJìĦľ
    0.10
     transition
    0.10
    Activations Density 0.121%

    No Known Activations