© 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. 41172
    Prev
    Next
    INDEX
    Explanations

    large numbers and quantities

    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
    äºĶåĪĨ
    -0.07
    åŃļ
    -0.07
    羿
    -0.07
    å¿Ĺæĺİ
    -0.07
     Ess
    -0.06
    åĩłåĪĨ
    -0.06
    winkel
    -0.06
     Koh
    -0.06
    éĥ½ä¸įéĶĻ
    -0.06
    -%
    -0.06
    POSITIVE LOGITS
     millions
    0.14
     enormous
    0.13
     thousands
    0.13
     colossal
    0.13
     billions
    0.13
     huge
    0.13
    æķ°çĻ¾ä¸ĩ
    0.13
    æķ°åįĥ
    0.13
     immense
    0.12
     gigantic
    0.12
    Activations Density 0.071%

    No Known Activations