© 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. 2237
    Prev
    Next
    INDEX
    Explanations

    Chinese/non-latin terms

    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
    essor
    -0.07
    iculum
    -0.06
     inout
    -0.06
    oncini
    -0.06
    æĸĽ
    -0.06
    èĮ¸
    -0.06
     lá»ĩ
    -0.06
     Martino
    -0.06
    è¡Ģ管çĺ¤
    -0.06
    itra
    -0.06
    POSITIVE LOGITS
    大åIJį
    0.08
    åIJĦç±»
    0.08
    wend
    0.08
    ä¹ĭ为
    0.08
    å²Ń
    0.07
    ãĢģãĢģ
    0.07
    ãĢģãĢģãĢģ
    0.07
    amay
    0.07
    å·´
    0.07
    绪
    0.07
    Activations Density 0.397%

    No Known Activations