© 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. 10899
    Prev
    Next
    INDEX
    Explanations

    that is

    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
    éĤ£å°±
    -0.08
    mts
    -0.07
    isman
    -0.07
    éĤ£éģĵ
    -0.07
    éĤ£ä¹Łæĺ¯
    -0.07
    ाय
    -0.07
    <TResult
    -0.07
    ÑĢое
    -0.07
    éĤ£å°±æĺ¯
    -0.07
    éĤ£
    -0.07
    POSITIVE LOGITS
    utra
    0.08
    ä»Ģä¹Īåij¢
    0.08
    erton
    0.08
    åı¤å±ĭ
    0.07
    毫ä¸į
    0.07
    å®ģåı¯
    0.07
    kert
    0.07
    presso
    0.07
    ledes
    0.07
    [:,:
    0.06
    Activations Density 0.030%

    No Known Activations