© 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. 56723
    Prev
    Next
    INDEX
    Explanations

    start of season/campaign

    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
    æľ«æľŁ
    -0.10
    æľĢåIJİä¸Ģ次
    -0.10
    Completed
    -0.08
     Completed
    -0.08
    -extra
    -0.08
    completed
    -0.08
    åľ¨æľĢåIJİ
    -0.08
    ç»ĵæ¡Ī
    -0.08
    å°±å®ĮæĪIJäºĨ
    -0.08
     Finish
    -0.07
    POSITIVE LOGITS
    èµ·å§ĭ
    0.21
     starting
    0.20
    çļĦå¼Ģå§ĭ
    0.19
    èµ·çĤ¹
    0.19
    çļĦ第ä¸ĢæŃ¥
    0.19
     starts
    0.18
     ìĭľìŀij
    0.18
    çļĦ第ä¸Ģ个
    0.18
    å¼Ģå§ĭ
    0.18
     beginning
    0.18
    Activations Density 0.646%

    No Known Activations