© 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. 11654
    Prev
    Next
    INDEX
    Explanations

    Byzantine

    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
    ÏĥÏĦά
    -0.10
    ìĿĺ
    -0.10
    emers
    -0.09
    esen
    -0.08
    isons
    -0.08
    esu
    -0.08
    ysÅĤ
    -0.08
     ziy
    -0.08
    머ëĭĪ
    -0.08
    çļĦéĢŁåº¦
    -0.08
    POSITIVE LOGITS
    nya
    0.11
    ting
    0.08
    ly
    0.08
    ÛĮ
    0.08
    £
    0.08
    átk
    0.08
    çļĦ
    0.08
    ب
    0.07
    loth
    0.07
    ìĿĦ
    0.07
    Activations Density 0.087%

    No Known Activations