© 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. 41966
    Prev
    Next
    INDEX
    Explanations

    definition/category/invention/copyright

    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
    aid
    -0.07
    åħ¨éĿ¢åIJ¯åĬ¨
    -0.07
    nest
    -0.07
    пил
    -0.06
     Beit
    -0.06
    ce
    -0.06
    åIJĦå¸Ĥ
    -0.06
    umbed
    -0.06
     totaled
    -0.06
    [text
    -0.06
    POSITIVE LOGITS
    ikel
    0.09
    edly
    0.08
    ught
    0.07
    zeÅĽ
    0.07
    ä¸ĢæĦı
    0.07
    éģĬ
    0.07
    gili
    0.07
    .isValid
    0.07
    åħ«ä»Ļ
    0.07
     undefeated
    0.07
    Activations Density 0.007%

    No Known Activations