© 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. 16321
    Prev
    Next
    INDEX
    Explanations

    char variable declarations

    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
    å¾·åįİ
    -0.09
    uler
    -0.08
    翼翼
    -0.08
    ergestellt
    -0.08
     fleste
    -0.07
    iglich
    -0.07
    erness
    -0.07
    pler
    -0.07
    ä¸įçIJĨ解
    -0.07
    ÑģмоÑĤÑĢиÑĤе
    -0.07
    POSITIVE LOGITS
    mony
    0.10
    ness
    0.09
    acters
    0.09
    trand
    0.08
    riott
    0.08
    bage
    0.08
    å¸Ĥ人æ°ijæ³ķéĻ¢
    0.08
    wel
    0.07
    cter
    0.07
    icum
    0.07
    Activations Density 0.034%

    No Known Activations