© 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. 17365
    Prev
    Next
    INDEX
    Explanations

    foreign language terms and translations

    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®īçļĦ
    -0.05
    ì¶ľ
    -0.05
    æł¹çļĦ
    -0.05
    åºľçļĦ
    -0.05
    pez
    -0.05
    èĤ²
    -0.05
     Wür
    -0.05
    屯
    -0.05
    hil
    -0.05
    æĦıæĮĩ
    -0.05
    POSITIVE LOGITS
    ast
    0.06
    æŀģ端
    0.06
    cede
    0.06
     пÑĢоведе
    0.05
     zad
    0.05
    ungg
    0.05
    pare
    0.05
    mir
    0.05
    izeit
    0.05
    lais
    0.05
    Activations Density 0.027%

    No Known Activations