© 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. 19379
    Prev
    Next
    INDEX
    Explanations

    attempt to

    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
    oja
    -0.09
     ìķĬìľ¼
    -0.07
    æŶæĬ¥
    -0.07
    ìį¨
    -0.07
     ìĿ¸íķ´
    -0.06
     demás
    -0.06
    ãģĭãģ¯
    -0.06
    tÃł
    -0.06
    à¹īว
    -0.06
    wend
    -0.06
    POSITIVE LOGITS
    رة
    0.07
    yclopedia
    0.06
    ue
    0.06
    £
    0.06
    edException
    0.05
    ثاÙĦ
    0.05
    ÑģÑı
    0.05
    ual
    0.05
    ÑĤеÑģÑĮ
    0.05
    大ä¸Ī夫
    0.05
    Activations Density 0.013%

    No Known Activations