© 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. 19415
    Prev
    Next
    INDEX
    Explanations

    finding non-English words

    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
    chan
    -0.06
    van
    -0.05
    6
    -0.05
    Cont
    -0.05
     pa
    -0.05
     im
    -0.05
    å¸ĥ
    -0.05
    èĭ¦
    -0.05
     jun
    -0.05
    op
    -0.05
    POSITIVE LOGITS
    emez
    0.08
    æĪIJçīĩ
    0.07
    yat
    0.07
    ä¸įæį¢
    0.07
    achim
    0.06
    á»ĩ
    0.06
    é¡¹çĽ®çļĦ建设
    0.06
    apres
    0.06
    lesh
    0.06
     Stazione
    0.06
    Activations Density 0.001%

    No Known Activations