© 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. 10659
    Prev
    Next
    INDEX
    Explanations

    flat terrain

    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
    ä¹Łä¸įè¦ģ
    -0.08
    éĥ½ä¸įåı¯èĥ½
    -0.07
    ä¹Łä¸į好
    -0.07
    è¿ĺä¸įå¦Ĥ
    -0.07
    olia
    -0.07
    ä¹Łä¸įåı¯èĥ½
    -0.07
    ssc
    -0.07
    æľīä¸įåIJĮçļĦ
    -0.06
     Shapiro
    -0.06
    æħ
    -0.06
    POSITIVE LOGITS
    符åIJĪè¦ģæ±Ĥ
    0.14
     yes
    0.14
     indeed
    0.13
    ç¡®å®ŀæĺ¯
    0.13
    ç¡®å®ŀ
    0.13
     âľĶ
    0.13
    符åIJĪ
    0.12
    è¿ĻæŃ£æĺ¯
    0.12
    没éĹ®é¢ĺ
    0.12
     âľĵ
    0.12
    Activations Density 0.012%

    No Known Activations