© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20359
    Prev
    Next
    INDEX
    Explanations

    making sure it is up-to-date

    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
    å®Ľ
    -0.06
    æĿ¡ä»¶æĺ¯
    -0.05
    archive
    -0.05
    æĢ»ç»ĵå¦Ĥä¸ĭ
    -0.05
    æĿ¡ä»¶çļĦ
    -0.05
    Else
    -0.05
    ÑĪаÑĤ
    -0.05
    erties
    -0.05
    åIJ¦åĪĻ
    -0.05
    agra
    -0.05
    POSITIVE LOGITS
    å°ijèµ°
    0.07
    itom
    0.06
    _deep
    0.06
    جÙĪÛĮ
    0.06
     formal
    0.05
    æł¹æį®ä¸ªäºº
    0.05
     mém
    0.05
    cross
    0.05
     gând
    0.05
    YRO
    0.05
    Activations Density 0.015%

    No Known Activations