© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9145
    Prev
    Next
    INDEX
    Explanations

    suggests or implies something

    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
    oudre
    -0.09
    æŀĦæĪIJçĬ¯ç½ªçļĦ
    -0.09
    è®
    -0.08
    джи
    -0.08
    ulé
    -0.08
    CRET
    -0.08
    Checksum
    -0.08
    าศ
    -0.08
    _NC
    -0.07
    éģĵæĿ¥
    -0.07
    POSITIVE LOGITS
     something
    0.10
     a
    0.09
     involvement
    0.09
     someone
    0.09
    èĢĮä¸Ķä¹Ł
    0.08
    ä¸Ģç§į
    0.08
     ìĹŃìĭľ
    0.08
    ä¸Ģ个éĹ®é¢ĺ
    0.08
    æľīäººåľ¨
    0.08
    è¿Ļæł·ä¸Ģç§į
    0.08
    Activations Density 0.038%

    No Known Activations