© 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. 43428
    Prev
    Next
    INDEX
    Explanations

    section headers, notes, options

    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
    t
    -0.07
    æľ¬èº«å°±æĺ¯
    -0.07
    缮æłĩæĺ¯
    -0.06
    uca
    -0.06
    é¦ĸåħĪæĺ¯
    -0.06
    estin
    -0.06
    éĿĴ
    -0.06
    ooks
    -0.06
    é¦ĸåħĪ
    -0.06
    ãĢħ
    -0.06
    POSITIVE LOGITS
    åºĶ注æĦı
    0.08
    غÙĬر
    0.07
    addOn
    0.07
    ungg
    0.07
     optionally
    0.07
    ×ķ׾×Ļ
    0.07
    .after
    0.07
    _maker
    0.07
    ä¸İåIJĮåѦ
    0.07
    amm
    0.07
    Activations Density 0.003%

    No Known Activations