© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21992
    Prev
    Next
    INDEX
    Explanations

    full path or class name

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    宵
    -0.06
    ovit
    -0.06
     giỼi
    -0.06
    eggi
    -0.06
    ools
    -0.06
    ä¿Ĭ
    -0.05
    æĪĴ
    -0.05
    主è¦ģä»İäºĭ
    -0.05
    rum
    -0.05
    å¥ĹçĶ¨
    -0.05
    POSITIVE LOGITS
    ุ
    0.06
    两ç§įæĸ¹å¼ı
    0.06
    çģ
    0.06
     ÙħÙĤØ·
    0.06
    resh
    0.06
    åįļ大
    0.06
    idenza
    0.06
    oste
    0.06
    anta
    0.05
    usses
    0.05
    Activations Density 0.012%

    No Known Activations