© 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. 8311
    Prev
    Next
    INDEX
    Explanations

    rates and indexes

    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
    以ä¸Ģ个
    -0.09
     nämlich
    -0.08
    ä¸įä»ħèĥ½å¤Ł
    -0.08
    æį¢åı¥è¯Ŀ说
    -0.08
    apis
    -0.07
    ä¹ĭæīĢ以
    -0.07
    è¿ĺåºĶ该
    -0.07
    .inf
    -0.07
    äºĭå®ŀä¸Ĭ
    -0.07
    èĥ½ä»¥
    -0.07
    POSITIVE LOGITS
    å°±æĺ¯äºĨ
    0.07
    ucker
    0.07
    à¸Ħืà¸Ń
    0.07
    æĺ¯åħ¶
    0.07
     accordingly
    0.07
    å°±æĺ¯è¿Ļ个
    0.07
    å°±æĺ¯æĪijçļĦ
    0.07
     is
    0.07
    å°±æĺ¯æĪij们çļĦ
    0.06
    å°±æĺ¯ä»ĸ
    0.06
    Activations Density 0.090%

    No Known Activations