© 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. 22485
    Prev
    Next
    INDEX
    Explanations

    č

    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
    uera
    -0.07
    oguÄĩ
    -0.07
    riture
    -0.07
     ÙħØ«ÙĦا
    -0.07
    çļĦåħ¶ä»ĸ
    -0.07
     silen
    -0.07
     Ãļl
    -0.07
     autres
    -0.07
     Especi
    -0.07
    cÄĥ
    -0.07
    POSITIVE LOGITS
    ity
    0.06
     N
    0.06
     $
    0.06
    æīĢåľ¨
    0.05
    !
    0.05
     \(
    0.05
     a
    0.05
    ↵↵
    0.05
     os
    0.05
    们
    0.05
    Activations Density 0.048%

    No Known Activations