© 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. 27657
    Prev
    Next
    INDEX
    Explanations

    progress of events or time

    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
    ikal
    -0.07
    è·ĥ
    -0.07
    çĪĨ
    -0.07
    è¿ĩåİ»ä¸Ģå¹´
    -0.07
    æµĭè¯ķç»ĵæŀľ
    -0.06
    轻轻ä¸Ģ
    -0.06
    inkt
    -0.06
    ç¿Ĵæħ£
    -0.06
    ä¹łæĥ¯
    -0.06
    rano
    -0.06
    POSITIVE LOGITS
     progress
    0.14
    æİ¥è¿ij尾声
    0.12
    -progress
    0.12
     Progress
    0.12
    _progress
    0.12
     progresses
    0.12
    è¿Ľåº¦
    0.11
     progressed
    0.11
     progressing
    0.11
     started
    0.11
    Activations Density 0.501%

    No Known Activations