© 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. 61915
    Prev
    Next
    INDEX
    Explanations

    ë, ü, ç

    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
     ÑıкобÑĭ
    -0.09
     appunto
    -0.08
     supposedly
    -0.08
     justement
    -0.07
    ategori
    -0.07
     вовÑģе
    -0.07
    åľ¨ä»ĸçľĭæĿ¥
    -0.07
     поÑĢой
    -0.07
    ¶
    -0.07
    agen
    -0.07
    POSITIVE LOGITS
    åIJĮåѦéĥ½
    0.08
    </think>
    0.07
    æĿı
    0.07
     analy
    0.07
    åĩĢåĪ©æ¶¦ä¸º
    0.07
    __:
    0.07
    æĪijæĺİçĻ½äºĨ
    0.06
    解éĩĬ说
    0.06
     approf
    0.06
     analyse
    0.06
    Activations Density 0.008%

    No Known Activations