© 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. 21973
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    ikon
    -0.07
    atas
    -0.07
    æĹłæ¯Ĵ
    -0.07
    ÑĢенное
    -0.07
    еÑģа
    -0.06
    quot
    -0.06
    æīĢéķ¿
    -0.06
    umber
    -0.06
    rolet
    -0.06
    åķĨä¼ļ
    -0.06
    POSITIVE LOGITS
    assin
    0.05
     re
    0.05
     t
    0.05
    ä¼´
    0.04
     pre
    0.04
     culture
    0.04
     Culture
    0.04
    çĽĺ
    0.04
    ¾
    0.04
     perennial
    0.04
    Activations Density 0.001%

    No Known Activations