© 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. 22384
    Prev
    Next
    INDEX
    Explanations

    world domination or change

    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
    夫æĸ¯åŁº
    -0.06
    bele
    -0.06
    aret
    -0.05
     ÙĪبÙĬÙĨ
    -0.05
    liness
    -0.05
    idan
    -0.05
    ä¹İ
    -0.05
    emberg
    -0.05
    odynam
    -0.05
    lieg
    -0.05
    POSITIVE LOGITS
    ewe
    0.06
     sequer
    0.05
    atus
    0.05
     ëĶ°
    0.05
    éĻĦ带
    0.05
    èĢĮå¼ķèµ·
    0.05
    colar
    0.05
    ä¸įåı¯éģ¿åħįçļĦ
    0.05
    ORTE
    0.05
    樣çļĦ
    0.05
    Activations Density 0.004%

    No Known Activations