© 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. 16750
    Prev
    Next
    INDEX
    Explanations

    manufacturing, improved, Africa, requested, reliability, human, kind

    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
    京
    -0.06
    S
    -0.05
    æī£
    -0.05
    æĤŁ
    -0.05
    æ¡Įä¸Ĭ
    -0.05
    误
    -0.05
    JR
    -0.05
    -0.05
    lore
    -0.05
    åıĭ
    -0.05
    POSITIVE LOGITS
    ingly
    0.07
     بÙĩØ°Ùĩ
    0.06
    itim
    0.06
    undef
    0.06
    alap
    0.06
    :numel
    0.06
     levado
    0.06
    æıIJé«ĺèĩªèº«
    0.06
     elseif
    0.05
    íķĺìĭľê¸°
    0.05
    Activations Density 0.005%

    No Known Activations