© 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. 50529
    Prev
    Next
    INDEX
    Explanations

    numbers mixed with words like "serious"

    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
    è´
    -0.07
    éĿŀçī©è´¨
    -0.06
    æľīåħ³åįķä½į
    -0.06
    æĹłæŶæĹłåĪ»
    -0.06
    广ä¹ī
    -0.06
     closest
    -0.06
    æ²ģ
    -0.06
    æĹłå¤Ħä¸įåľ¨
    -0.06
    ä¸į失
    -0.06
    iola
    -0.06
    POSITIVE LOGITS
     kombin
    0.09
     combination
    0.08
    主æĶ»
    0.08
    ç«ŀäºīæ¿ĢçĥĪ
    0.08
    combined
    0.08
    itech
    0.08
    mixed
    0.08
    enor
    0.08
     heavyweight
    0.08
    ilik
    0.08
    Activations Density 0.582%

    No Known Activations