© 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. 19491
    Prev
    Next
    INDEX
    Explanations

    French, German, and English phrasing

    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
    æĢĿæºIJ
    -0.06
    cini
    -0.06
    elay
    -0.05
    æ·«
    -0.05
    è¿ĩåįĬ
    -0.05
    éĻĦè¿ij
    -0.05
    æĮĩæĮ¥
    -0.05
    æľīéĻIJ
    -0.05
    ä»ĺæģ¯
    -0.05
    ä¸įèµ·çľ¼
    -0.05
    POSITIVE LOGITS
    igm
    0.07
    oha
    0.06
    ائÙĦ
    0.06
    agl
    0.06
    apl
    0.06
    è¯ĬæĸŃ
    0.06
    ä¹ŁæĹłæ³ķ
    0.06
    urn
    0.06
    ä¸ĢåĪ»
    0.06
     dijal
    0.06
    Activations Density 0.002%

    No Known Activations