© 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. 22612
    Prev
    Next
    INDEX
    Explanations

    in

    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
    -0.06
    usco
    -0.06
    åıĬéĻĦåĬł
    -0.06
    梢
    -0.06
    æĬĵä½ıäºĨ
    -0.06
    osi
    -0.06
    åħ¥å¾®
    -0.06
    sink
    -0.06
    æĹłæĢ¨
    -0.06
    -la
    -0.05
    POSITIVE LOGITS
    æĮ¨
    0.06
     graz
    0.05
    ä¸įæĸŃçļĦ
    0.05
    klad
    0.05
    ç¡Ŀéħ¸
    0.05
    åIJ«
    0.05
     aberr
    0.05
     fede
    0.05
     nowhere
    0.05
    ØŃدث
    0.05
    Activations Density 0.002%

    No Known Activations