© 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. 23989
    Prev
    Next
    INDEX
    Explanations

    later or someday

    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
    ä¸ĬæľĪ
    -0.07
    -anchor
    -0.07
    åľ¨æĪijçľĭæĿ¥
    -0.07
    æĺ¨å¤ľ
    -0.07
    èĢģ夫人
    -0.06
    åĪĿæŃ¥
    -0.06
    ovsky
    -0.06
    åĭĩ
    -0.06
    æĺ¨æĻļ
    -0.06
    -helper
    -0.06
    POSITIVE LOGITS
     someday
    0.16
     nanti
    0.14
    å±ĬæŶ
    0.13
    åĨįæĿ¥
    0.12
     later
    0.12
    以åIJİåĨį
    0.12
    ä»Ģä¹ĪæŶåĢĻ
    0.12
     future
    0.11
    åĪ°æŶåĢĻ
    0.11
    æĢ»æľīä¸Ģ天
    0.11
    Activations Density 0.260%

    No Known Activations