© 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. 15734
    Prev
    Next
    INDEX
    Explanations

    code block syntax

    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
    ç»ĪçĤ¹
    -0.08
    æ³ķåºŃ
    -0.08
    å°ijå¹´çļĦ
    -0.07
    ãģ°ãģĭãĤĬ
    -0.07
    áĢĽáĢ¾
    -0.07
    ocos
    -0.07
    å¤ļæľĪ
    -0.07
    kowski
    -0.07
    é¦Ĩéķ¿
    -0.07
    OCA
    -0.07
    POSITIVE LOGITS
    æĺ¯ä¸Ģç§į常è§ģçļĦ
    0.07
    åħ·æľīå¾Ī好çļĦ
    0.07
    è¶Ĭ大
    0.07
    _urls
    0.07
    oten
    0.07
    ä½ľä¸ºä¸Ģç§į
    0.06
    todo
    0.06
    ä¸Ģ个ç®ĢåįķçļĦ
    0.06
    mania
    0.06
     reasonable
    0.06
    Activations Density 0.200%

    No Known Activations