© 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. 13022
    Prev
    Next
    INDEX
    Explanations

    docstring parameters and license

    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
    ogu
    -0.08
    ä»İé«ĺ
    -0.08
     Spo
    -0.07
    å¤ļåı°
    -0.07
    çĶ±é«ĺ
    -0.07
     <!--<
    -0.07
     bravo
    -0.06
     fiercely
    -0.06
    SCALL
    -0.06
    åĩºçİ°çļĦ
    -0.06
    POSITIVE LOGITS
    .Must
    0.07
    asis
    0.07
    empl
    0.07
    uncan
    0.07
    bor
    0.07
    æĸ¹æĸ¹éĿ¢
    0.07
    queeze
    0.07
    emplate
    0.07
    asic
    0.06
    вÑĸÑĢ
    0.06
    Activations Density 0.001%

    No Known Activations