© 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. 62376
    Prev
    Next
    INDEX
    Explanations

    hurry, late, early, time, immediately

    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
    ourd
    -0.07
    antos
    -0.07
    æĽ´æ·±
    -0.07
    agues
    -0.06
    åı¯ä»¥æĶ¾å¿ĥ
    -0.06
    çľĭä¸į
    -0.06
    ç´¯äºĨ
    -0.06
    reamble
    -0.06
    ç»ĪæĹ¥
    -0.06
     underlying
    -0.06
    POSITIVE LOGITS
    éĶĻè¿ĩäºĨ
    0.20
    éĶĻè¿ĩ
    0.16
    è¶ĬæĹ©
    0.15
    æĬĵä½ıäºĨ
    0.13
    éĮ¯éģİ
    0.13
    æĬĵä½ı
    0.13
    çªĹåı£
    0.13
    éĶĻè¿ĩçļĦ
    0.13
     timely
    0.13
    è¶ģ
    0.13
    Activations Density 0.384%

    No Known Activations