© 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. 40824
    Prev
    Next
    INDEX
    Explanations

    Numpy, collections, deposit, exception

    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
    ä¼Łäºº
    -0.08
    θη
    -0.08
    avage
    -0.08
    olon
    -0.07
    MAND
    -0.07
    æļĸæļĸ
    -0.07
    gge
    -0.07
    odb
    -0.07
    ÏĨε
    -0.07
    szt
    -0.07
    POSITIVE LOGITS
    Ïģιν
    0.06
    -specific
    0.06
     hone
    0.06
    heck
    0.06
     Hari
    0.06
    ải
    0.06
    å±ħ
    0.06
    omar
    0.06
    bury
    0.06
     Christian
    0.05
    Activations Density 0.768%

    No Known Activations