© 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. 15852
    Prev
    Next
    INDEX
    Explanations

    years, months, decade

    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
    ä»ĬåIJİçļĦ
    -0.09
    å¾Īå¿«çļĦ
    -0.09
     soon
    -0.08
    ä¸įä¹ħçļĦå°ĨæĿ¥
    -0.08
     ASAP
    -0.08
     quickly
    -0.08
    æĹ¥åIJİçļĦ
    -0.08
     futuras
    -0.08
     futura
    -0.08
     shortly
    -0.08
    POSITIVE LOGITS
    积累çļĦ
    0.13
    ä¹ĭä¹ħ
    0.13
    ä¸ĢçĽ´åľ¨
    0.11
    积累
    0.11
     accumulated
    0.10
    ä¹ħçļĦ
    0.10
    ä¸Ģ缴æĺ¯
    0.10
    以æĿ¥çļĦ
    0.10
    积累äºĨ
    0.10
     boyunca
    0.10
    Activations Density 0.751%

    No Known Activations