© 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. 24107
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and dimensions

    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
     Vernon
    -0.07
     Bev
    -0.07
    èĩªä½ľ
    -0.07
    bef
    -0.07
    ç¬ĥ
    -0.07
    椿
    -0.07
    yra
    -0.07
    à¹ģà¸Ľà¸¥à¸ĩ
    -0.07
    verages
    -0.07
    ÑĢев
    -0.07
    POSITIVE LOGITS
    è¡¡éĩı
    0.08
     measure
    0.08
    ewidth
    0.08
     ÙĪعدد
    0.08
    opus
    0.08
    ä¸Ģæķ°
    0.07
    imum
    0.07
     measures
    0.07
     Infinity
    0.07
    Infinity
    0.07
    Activations Density 0.017%

    No Known Activations