© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19569
    Prev
    Next
    INDEX
    Explanations

    åĪĨçļĦ

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects characters from non-Latin scripts and special characters found in various foreign languages.

    oai_token-act-pair · gemini-2.5-flashTriggered by @alphav00
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;/*
    -0.05
    upi
    -0.05
    èĮ«çĦ¶
    -0.05
    à¸ģระà¸Ķัà¸ļ
    -0.05
    aurais
    -0.05
    åıĬåĪ©æģ¯
    -0.05
    è¿Ļé¢Ĺ
    -0.05
     implicitly
    -0.05
    akin
    -0.05
    alas
    -0.05
    POSITIVE LOGITS
    å§ĵ
    0.06
    ä»Ģä¹ĪçļĦ
    0.05
    失信被æī§è¡Į人
    0.05
    клад
    0.05
    æĹ¶è¾°
    0.05
    马ä¸Ĭ
    0.05
    enca
    0.05
    åģļå¾Ĺ
    0.05
     ì·¨
    0.05
    å¾Īå¥½åľ°
    0.05
    Activations Density 0.008%

    No Known Activations