© 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. 22382
    Prev
    Next
    INDEX
    Explanations

    registered, converting, numbers

    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
    æıIJ
    -0.06
    æĭĽ
    -0.06
    emo
    -0.06
    jen
    -0.06
    æݪ
    -0.06
     bid
    -0.05
    atan
    -0.05
    åĩºåħ¥
    -0.05
    ä¸ģ
    -0.05
     dram
    -0.05
    POSITIVE LOGITS
    beeld
    0.07
    ODO
    0.06
    ä¸ĩäºĭå¦ĤæĦı
    0.06
    VERY
    0.06
    çļĦéĩįè¦ģä¾Ŀæį®
    0.06
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    0.06
    é¢Ħ计åĪ°
    0.06
    acqu
    0.06
     коÑĢе
    0.05
     Unt
    0.05
    Activations Density 0.011%

    No Known Activations