© 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. 16623
    Prev
    Next
    INDEX
    Explanations

    date and time formats

    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
    æĥ¯
    -0.06
    off
    -0.05
    æĬ¬
    -0.05
     Pist
    -0.05
    builtin
    -0.05
    hos
    -0.05
    åģı
    -0.05
    .edu
    -0.05
    æľīæĦı
    -0.05
    æģ©
    -0.05
    POSITIVE LOGITS
    ortal
    0.06
    åĨįçĤ¹åĩ»
    0.06
    ikul
    0.06
    rawy
    0.06
    ÑĢемен
    0.06
    大åĪ°
    0.06
     Juta
    0.06
    emporary
    0.06
    mous
    0.06
    ysi
    0.05
    Activations Density 0.035%

    No Known Activations