© 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. 16577
    Prev
    Next
    INDEX
    Explanations

    roman numeral prefixes

    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
    æ¸ł
    -0.06
    Ä
    -0.05
    å¦Ĥå®ŀ
    -0.05
    ä½İéĢŁ
    -0.05
    chemes
    -0.05
    _AUTHOR
    -0.05
     schemes
    -0.05
     fields
    -0.05
    åħ¶ä»ĸæĸ¹å¼ı
    -0.04
    kod
    -0.04
    POSITIVE LOGITS
    Ñħло
    0.07
    teilung
    0.06
     haus
    0.06
    urch
    0.06
    ylon
    0.06
     atro
    0.06
    rescia
    0.06
    ulton
    0.06
    зок
    0.06
     congratulations
    0.06
    Activations Density 0.001%

    No Known Activations