© 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. 15883
    Prev
    Next
    INDEX
    Explanations

    conduct, behavior, etiquette

    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
     honeymoon
    -0.08
    è¾Ł
    -0.08
    _race
    -0.08
    è¿ŀå¤ľ
    -0.07
    忽æĤł
    -0.07
    è¿ŀåIJĮ
    -0.07
    ç»ıéªĮ丰å¯ĮçļĦ
    -0.07
     ÑĢиÑģков
    -0.07
    æīĭæĬĬæīĭ
    -0.07
     ris
    -0.07
    POSITIVE LOGITS
    è¡Į为è§ĦèĮĥ
    0.15
    举æŃ¢
    0.12
     etiquette
    0.12
    åħ»æĪIJèī¯å¥½çļĦ
    0.11
     behavior
    0.11
    è¨Ģè¡Į
    0.11
    èĩªè§ī
    0.11
     behaviors
    0.10
    èĩªå¾ĭ
    0.10
    æķ´æ´ģ
    0.10
    Activations Density 0.072%

    No Known Activations