© 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. 25688
    Prev
    Next
    INDEX
    Explanations

    numbers and code snippets

    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
    ancy
    -0.08
    ãģ°ãģĭãĤĬ
    -0.08
    azzo
    -0.07
    ;!
    -0.07
    夫妻æĦŁæĥħ
    -0.07
    ragon
    -0.07
    žel
    -0.07
    azu
    -0.07
    eced
    -0.07
    uille
    -0.07
    POSITIVE LOGITS
    âĢ¦âĢ¦ãĢĤ
    0.07
    æIJŃ
    0.07
    PAGE
    0.07
    ...",
    0.07
    éĺ¿æĭī伯
    0.07
    åĴĮä¸ĭ
    0.06
    ----</
    0.06
    -/
    0.06
    ä¿Ŀéĩį
    0.06
    à²Ń
    0.06
    Activations Density 0.013%

    No Known Activations