© 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. 16664
    Prev
    Next
    INDEX
    Explanations

    England, Wales, Scotland

    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
     close
    -0.07
     clos
    -0.06
    éĻĦè¿ijæľī
    -0.06
    itz
    -0.06
    è¿ijãģıãģ«
    -0.05
    close
    -0.05
     ÑĩеÑĢе
    -0.05
    ä¸Ģç³»åĪĹ
    -0.05
    æŀķ
    -0.05
    è¿ijè·Ŀ离
    -0.05
    POSITIVE LOGITS
    éĿ¢ä¸Ĭ
    0.06
    chs
    0.06
    raga
    0.06
    éĥ¨åĪĨ
    0.06
    è¿Ļéĥ¨åĪĨ
    0.06
    براء
    0.06
    uga
    0.06
    è¡«
    0.06
    éĥ¨åĪĨæĺ¯
    0.06
    heads
    0.06
    Activations Density 0.027%

    No Known Activations