© 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. 30283
    Prev
    Next
    INDEX
    Explanations

    called or named

    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
     either
    -0.07
     anything
    -0.07
    IELD
    -0.07
    éĥ½æĺ¯åı¯ä»¥
    -0.07
    visor
    -0.07
    éĥ½æĺ¯ä¸Ģæł·çļĦ
    -0.06
     anyone
    -0.06
    unti
    -0.06
    æł¹æį®ä¸įåIJĮçļĦ
    -0.06
    第ä¸Ģ家
    -0.06
    POSITIVE LOGITS
    åı«åģļ
    0.12
    åı«
    0.11
    åIJįåı«
    0.11
     namens
    0.10
     called
    0.10
     recently
    0.09
     bernama
    0.09
    åIJį为
    0.09
     назÑĭваеÑĤÑģÑı
    0.08
    åı«ä»Ģä¹Ī
    0.08
    Activations Density 1.855%

    No Known Activations