© 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. 22437
    Prev
    Next
    INDEX
    Explanations

    checking for file existence

    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
    ovnÃŃ
    -0.06
     "
    -0.05
    repid
    -0.05
    çļĦåŃĺåľ¨
    -0.05
    åŃĺåľ¨çļĦ
    -0.05
    åı¯è§ģ
    -0.05
    å®ĥä»¬åľ¨
    -0.05
     Banc
    -0.05
     Far
    -0.05
    veld
    -0.05
    POSITIVE LOGITS
    aha
    0.06
    éry
    0.06
    inand
    0.06
    (.)
    0.06
     geïn
    0.06
     últim
    0.06
     wisdom
    0.06
    agon
    0.06
     اÙĦÙħÙĬت
    0.06
    lian
    0.06
    Activations Density 0.004%

    No Known Activations