© 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. 3811
    Prev
    Next
    INDEX
    Explanations

    Nominal values and counts

    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
    æ³ģ
    -0.07
    eman
    -0.07
    kar
    -0.07
     squ
    -0.07
    _tokenize
    -0.07
    ë°°
    -0.07
    å¹´çļĦæŶåĢĻ
    -0.07
    implode
    -0.07
    æľĢ主è¦ģçļĦ
    -0.07
     ÐŁÐ¾Ð»Ð¾
    -0.06
    POSITIVE LOGITS
     Nom
    0.08
    å®ŀéĻħ
    0.08
    åľ¨æĸ°çļĦ
    0.08
    nom
    0.08
    åIJįä¹ī
    0.08
    åİŁå®ļ
    0.08
    Nom
    0.08
     aparent
    0.08
    æľ¬èĥ½
    0.08
     nominal
    0.07
    Activations Density 0.010%

    No Known Activations