© 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. 18483
    Prev
    Next
    INDEX
    Explanations

    Russian and Chinese language usage

    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
    ãģĺãĤģ
    -0.07
    ä¸ĭäºĨ
    -0.07
    ÑģÑı
    -0.07
    Ľ
    -0.07
    Ùħس
    -0.06
    áĥIJáĥĻ
    -0.06
    çļĦåĬłå·¥
    -0.06
    linger
    -0.06
    å¹³äºĨ
    -0.06
    беÑĢиÑĤе
    -0.06
    POSITIVE LOGITS
    endo
    0.06
    çļĦæĺ¯
    0.06
    ship
    0.06
    ä½Ĩä¸įéĻIJäºİ
    0.05
    sg
    0.05
    ä¸ĢäºĽ
    0.05
    ä¸Ģ家
    0.05
    anzas
    0.05
    sWith
    0.05
    ä¸ĢåĪĩ
    0.05
    Activations Density 0.016%

    No Known Activations