© 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. 16899
    Prev
    Next
    INDEX
    Explanations

    x and y coordinates

    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
    Not in Any Lists

    No Comments

    Negative Logits
    é¦ĸ
    -0.06
    åį³
    -0.06
    åħĪè¿Ľ
    -0.06
    çŁ³
    -0.05
    åIJįåı«
    -0.05
    Ø«ÙĨ
    -0.05
    好
    -0.05
    l
    -0.05
    åŃĺåľ¨
    -0.05
    à¸Ŀ
    -0.05
    POSITIVE LOGITS
     penj
    0.07
    åIJĦèī²
    0.07
    åIJĦå¼ı
    0.07
     gunmen
    0.06
    大ä¸Ń
    0.06
     borne
    0.06
    åIJĦé¡ŀ
    0.06
    ahaha
    0.06
    pez
    0.05
    ä¸ĢæĿ¡é¾Ļ
    0.05
    Activations Density 0.036%

    No Known Activations