© 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. 28956
    Prev
    Next
    INDEX
    Explanations

    relevant data

    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
    .cms
    -0.08
    ises
    -0.08
    åħĪçĥĪ
    -0.07
    ctest
    -0.07
    ëij
    -0.07
    atures
    -0.07
    Ñļ
    -0.07
    itera
    -0.07
     [[[
    -0.07
    度åģĩåĮº
    -0.06
    POSITIVE LOGITS
     PhD
    0.07
    æ§Ľ
    0.07
     lon
    0.07
    heed
    0.07
    åľ¨ä»ĬåIJİçļĦå·¥ä½ľä¸Ń
    0.07
     пеÑĢÑģо
    0.06
    çłĶ究èĢħ
    0.06
    ÑģÑĤен
    0.06
     Tav
    0.06
    åħ¶ä»ĸ人
    0.06
    Activations Density 0.026%

    No Known Activations