© 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. 22582
    Prev
    Next
    INDEX
    Explanations

    extremes or opposition

    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
    æĸĹ
    -0.06
    éĻĦåĬł
    -0.06
    имо
    -0.06
    max
    -0.06
     heavier
    -0.06
    æ©¡
    -0.06
    éĩį
    -0.06
    åŁ¹
    -0.06
    urin
    -0.06
    åīĸèħ¹
    -0.05
    POSITIVE LOGITS
    åį·åħ¥
    0.06
     ine
    0.05
    为äºĨéģ¿åħį
    0.05
    以éģ¿åħį
    0.05
    è¿ĩ度
    0.05
     overs
    0.05
    awl
    0.05
     EITHER
    0.05
     Vive
    0.05
     adil
    0.05
    Activations Density 0.116%

    No Known Activations