© 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. 27427
    Prev
    Next
    INDEX
    Explanations

    remaining time or position

    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
    tick
    -0.07
    æĶĢæ¯Ķ
    -0.06
    iale
    -0.06
    æµ®ãģĭ
    -0.06
    ingk
    -0.06
    СÐļ
    -0.06
    abb
    -0.06
     tick
    -0.06
     Cre
    -0.06
    ialis
    -0.06
    POSITIVE LOGITS
    åIJİç»Ń
    0.13
    åIJİç»ŃçļĦ
    0.12
    remaining
    0.12
     remaining
    0.11
     future
    0.11
    Remaining
    0.11
     subsequent
    0.11
     Remaining
    0.11
    æľªæĿ¥
    0.11
    _remaining
    0.11
    Activations Density 0.048%

    No Known Activations