© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22613
    Prev
    Next
    INDEX
    Explanations

    questions, explanations, or speed

    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
    Negative Logits
    ä¹ł
    -0.06
    ÙħÙĦت
    -0.06
    yo
    -0.06
     captures
    -0.06
    ÑĨей
    -0.06
    æĶĿ
    -0.06
    è§ĦåĪĴ设计
    -0.06
    oux
    -0.06
     problematic
    -0.06
     fo
    -0.06
    POSITIVE LOGITS
     roda
    0.06
    åĨį次
    0.06
    éĿŀ
    0.05
    ern
    0.05
    åĨį度
    0.05
    åĥıåľ¨
    0.05
    Need
    0.05
    åĽłä¸ºè¿Ļ个
    0.05
    åĨį
    0.05
     needed
    0.05
    Activations Density 0.129%

    No Known Activations