© 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. 9541
    Prev
    Next
    INDEX
    Explanations

    yes it can

    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
    åı¯èĥ½è¦ģ
    -0.08
    åıªæľīä¸Ģ个
    -0.08
    æľĢ大éĻIJ度
    -0.07
    åıªèĥ½
    -0.07
    ä¸Ģä¸ĭåŃIJ
    -0.07
    å°±åıªèĥ½
    -0.07
    ãģ£ãģıãĤĬ
    -0.07
    ä¸įèĥ½æľī
    -0.07
    åĢ¾åIJijäºİ
    -0.07
     ÐĹаÑĤо
    -0.07
    POSITIVE LOGITS
     durchaus
    0.12
     indeed
    0.12
    ä¹Łç¡®å®ŀ
    0.11
    èĻ½çĦ¶ä¸įæĺ¯
    0.11
     albeit
    0.11
    ç¡®å®ŀ
    0.10
     вполне
    0.10
    ä¸įä¹ı
    0.10
    ç¡®æľī
    0.10
    åı¯ä»¥çļĦ
    0.10
    Activations Density 0.087%

    No Known Activations