© 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. 55411
    Prev
    Next
    INDEX
    Explanations

    function definitions and code errors

    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
    ά
    -0.07
    壮
    -0.07
     occ
    -0.06
     Hayes
    -0.06
    åįĬ
    -0.06
    åĢª
    -0.06
     Bris
    -0.06
    åĢºæĿĥåĢºåĬ¡
    -0.06
    ä¸įä»ħ
    -0.06
    çħŀ
    -0.06
    POSITIVE LOGITS
     ÂŃ
    0.08
    registre
    0.08
    ริม
    0.07
    à¸£à¸¸à¸Ľ
    0.07
    嬢
    0.07
    ª½
    0.07
     STDERR
    0.07
    âĢIJ
    0.07
    urm
    0.07
     STDOUT
    0.07
    Activations Density 0.027%

    No Known Activations