© 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. 12663
    Prev
    Next
    INDEX
    Explanations

    with Facebook or Berlin

    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
    ä¸į解
    -0.07
    ersh
    -0.07
    çŃ
    -0.06
    å½°
    -0.06
     Harness
    -0.06
    ouro
    -0.06
    ä¸įèĻļ
    -0.06
    éħİ
    -0.06
    ä¸įå®ī
    -0.06
    _aw
    -0.06
    POSITIVE LOGITS
    åĽ½äº§
    0.08
    诸å¦Ĥ
    0.08
    åIJĦç§į
    0.08
    åĽłç´łå½±åĵį
    0.08
    çļĦåIJĦç§į
    0.08
    áĢĢáĢº
    0.07
    åĽłç´łçļĦå½±åĵį
    0.07
    äºŃäºŃ
    0.07
    æ¥Ń
    0.07
    æŁIJç§į
    0.07
    Activations Density 0.223%

    No Known Activations