© 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. 48693
    Prev
    Next
    INDEX
    Explanations

    years or centuries

    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
    è¿ĶåĽŀåĪĹ表
    -0.08
    æļĤæŶ
    -0.07
    URRE
    -0.07
    饿äºĨ
    -0.07
    èĻij
    -0.07
    æľĢæĸ°æĽ´æĸ°
    -0.07
    鸳鸯
    -0.07
    æļĤæŶçļĦ
    -0.07
     ìŀłìĭľ
    -0.07
    öt
    -0.07
    POSITIVE LOGITS
     retrospect
    0.20
     retrospective
    0.18
     hindsight
    0.16
    åĽŀ溯
    0.16
    indsight
    0.14
    追å¿Ĩ
    0.14
     retros
    0.14
    追溯
    0.14
    åĽŀå¿Ĩ
    0.13
     retro
    0.13
    Activations Density 0.658%

    No Known Activations