© 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. 23369
    Prev
    Next
    INDEX
    Explanations

    time travel and timelines

    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
    å±ħæĺĵ
    -0.08
    æŁ¥çľĭåħ¨éĥ¨
    -0.07
    鼨åIJİ
    -0.07
    cita
    -0.07
    *size
    -0.07
    ä¹ĭæĢ¥
    -0.07
     {*
    -0.07
    è¢«ä¾ĽåºĶåķĨ
    -0.07
    åħįè´¹åľ¨çº¿
    -0.07
    inna
    -0.07
    POSITIVE LOGITS
     timeline
    0.11
     timelines
    0.10
     Timeline
    0.09
    timeline
    0.09
    æŶéĹ´çĤ¹
    0.09
    ä¸İçİ°å®ŀ
    0.09
    éĶĻä½į
    0.09
     caus
    0.08
    Timeline
    0.08
    æľªæĿ¥çļĦ
    0.08
    Activations Density 0.086%

    No Known Activations