© 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. 22476
    Prev
    Next
    INDEX
    Explanations

    by [action]

    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
    Weiter
    -0.07
     regard
    -0.05
    ife
    -0.05
    æ¨¡æł·
    -0.05
    ertif
    -0.05
    å¾Ģ
    -0.05
    æѤæŶ
    -0.05
    ÑĤива
    -0.05
    á»ģ
    -0.05
    模樣
    -0.05
    POSITIVE LOGITS
    ת
    0.06
    èĽ®
    0.06
    åı¯æıIJä¾Ľ
    0.06
    å°±åĪ«
    0.06
    бÑĢан
    0.06
    åIJİçļĦ
    0.05
    æĺŃ
    0.05
    ureau
    0.05
    æ´ĭ
    0.05
    maid
    0.05
    Activations Density 0.014%

    No Known Activations