© 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. 51139
    Prev
    Next
    INDEX
    Explanations

    loosen or break fasteners, ice, rock, or tissues

    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
    åĸľæĢĴ
    -0.08
    Äįu
    -0.07
    urve
    -0.07
    è·ij
    -0.07
     shuffle
    -0.07
    è¿Ľä¸ĢæŃ¥è§ĦèĮĥ
    -0.07
    æĥĬéŃĤ
    -0.07
     hed
    -0.07
    诽
    -0.07
     soát
    -0.07
    POSITIVE LOGITS
    æĶ»åĿļ
    0.14
    æĶ»åĿļåħĭéļ¾
    0.11
    çł´éĻ¤
    0.11
     stubborn
    0.11
    ä¸įçł´
    0.11
    çªģçł´åı£
    0.11
    çł´è§£
    0.10
    breaking
    0.10
    解éļ¾
    0.10
    çĵ¦è§£
    0.09
    Activations Density 0.223%

    No Known Activations