© 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. 10993
    Prev
    Next
    INDEX
    Explanations

    programming definitions and structures

    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
    loyd
    -0.09
    ä¸įæİī
    -0.07
    æ¶ķ
    -0.07
    ingan
    -0.07
    oti
    -0.07
     нада
    -0.07
     nai
    -0.07
    дол
    -0.07
    venus
    -0.07
    lops
    -0.07
    POSITIVE LOGITS
     whose
    0.09
    åIJįåı«
    0.08
    çķĮçļĦ
    0.08
    smith
    0.08
    elize
    0.07
    åIJį为
    0.07
    hood
    0.07
    ante
    0.07
    ifier
    0.07
     den
    0.06
    Activations Density 0.020%

    No Known Activations