© 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. 2566
    Prev
    Next
    INDEX
    Explanations

    go away or to the right

    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
    ettel
    -0.07
    ä¸įåı¯æĪĸ缺çļĦ
    -0.06
    èIJ¦ç»ķ
    -0.06
    æŃ£åĽłä¸º
    -0.06
    :host
    -0.06
    çį
    -0.06
     ex
    -0.06
    åıįæŃ£
    -0.06
    rapper
    -0.06
    æĥ¯äºĨ
    -0.06
    POSITIVE LOGITS
    ä½Ĩè¿Ļ
    0.11
    ä½Ĩè¿Ļç§į
    0.09
    åı¯ä»¥èĢĥèĻij
    0.09
    è¿Ļåı¯èĥ½
    0.09
    è¿Ļåı¯èĥ½æĺ¯
    0.08
    æĮºå¥½çļĦ
    0.08
    ä¸įéĶĻçļĦ
    0.08
    ä¸įè¿ĩè¿Ļ
    0.08
    ä½Ĩæĺ¯è¿Ļ
    0.08
    æĺ¥æĿ¥
    0.07
    Activations Density 0.034%

    No Known Activations