© 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. 63926
    Prev
    Next
    INDEX
    Explanations

    why this occurs

    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
    å¿ĻçĿĢ
    -0.06
    ilah
    -0.06
    ä¹ĭ交
    -0.06
    ä»Ģä¹ĪæĦıæĢĿ
    -0.06
    åŃĺ
    -0.06
    ays
    -0.06
    éħį以
    -0.06
    æł¹æį®éľĢè¦ģ
    -0.06
    æŃ£ç»ı
    -0.06
    cab
    -0.06
    POSITIVE LOGITS
    è¿Ļä¹Īå¤ļ
    0.14
    è¿Ļä¹Īå¤ļçļĦ
    0.14
    è¿Ļä¹Ī大çļĦ
    0.14
    è¿Ļä¹Ī大
    0.14
    è¿Ļä¹Īå¿«
    0.13
     ÑģÑĤолÑĮ
    0.13
    è¿Ļä¹Īå¤ļ人
    0.13
    ãģĵãĤĵãģªãģ«
    0.13
    éĢĻ麼å¤ļ
    0.13
    å¦ĤæѤ
    0.12
    Activations Density 0.381%

    No Known Activations