© 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. 46198
    Prev
    Next
    INDEX
    Explanations

    code appending or adding

    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
    atria
    -0.08
    æľīä¸ĢèĤ¡
    -0.07
    иÑģк
    -0.07
    enis
    -0.07
    à¹Ģà¸ķà¹ĩมà¸Ĺีà¹Ī
    -0.07
    à¹Ģà¸ķà¹ĩม
    -0.07
    enzo
    -0.07
    大客æĪ·
    -0.07
    redit
    -0.06
    äºĭçī©çļĦ
    -0.06
    POSITIVE LOGITS
     accum
    0.10
     accumulating
    0.09
     accumulate
    0.09
    åĪĿæŃ¥
    0.09
    积累
    0.09
     Accum
    0.09
    累计
    0.09
     already
    0.09
    æ·»åĬł
    0.09
    ++]
    0.09
    Activations Density 0.053%

    No Known Activations