© 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. 31882
    Prev
    Next
    INDEX
    Explanations

    mathematical notation with superscripts/indices

    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
    &apos
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    Ñģно
    -0.06
    ä¸ĬåĽ¾
    -0.06
    дÑİ
    -0.06
    æ¯ĽåĪ©
    -0.05
    ฯ
    -0.05
    gau
    -0.05
    AIN
    -0.05
    ↵
    -0.05
    POSITIVE LOGITS
    stig
    0.09
    ogh
    0.09
    ittest
    0.08
    atria
    0.08
    omia
    0.08
    igue
    0.08
    esty
    0.08
    ÎŃÏģα
    0.08
    çĹĩæĤ£èĢħ
    0.08
    _subtype
    0.08
    Activations Density 0.019%

    No Known Activations