© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63961
    Prev
    Next
    INDEX
    Explanations

    code return statements

    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
    hnya
    -0.08
    اÙĨت
    -0.08
    ache
    -0.08
    ograd
    -0.08
    idar
    -0.08
    umper
    -0.07
     Nâng
    -0.07
    æľīå¥ĸ
    -0.07
    orca
    -0.07
    heim
    -0.07
    POSITIVE LOGITS
    ä¼į
    0.07
    NullOr
    0.07
    eturn
    0.06
    æ»ĵ
    0.06
    utas
    0.06
    obel
    0.06
    åīĶ
    0.06
    è¤
    0.06
     Wohl
    0.06
     abs
    0.06
    Activations Density 0.001%

    No Known Activations