© 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. 16584
    Prev
    Next
    INDEX
    Explanations

    state changes or configuration

    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
    wäl
    -0.06
    atel
    -0.06
    ubes
    -0.05
    eda
    -0.05
    ungan
    -0.05
    çļĦä¿¡ä»»
    -0.05
    å¾ĭ
    -0.05
    icale
    -0.05
    çĨł
    -0.05
     Moran
    -0.05
    POSITIVE LOGITS
    åľ¨æľª
    0.07
     definit
    0.06
    空éĹ´
    0.06
    band
    0.05
    éĢļè¿ĩåIJİ
    0.05
    immen
    0.05
    å°ıåŃIJ
    0.05
    å®ļäºĨ
    0.05
     bang
    0.05
    èī²è°ĥ
    0.05
    Activations Density 0.001%

    No Known Activations