© 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. 22497
    Prev
    Next
    INDEX
    Explanations

    laundry and washing machines

    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
    trop
    -0.07
    ergestellt
    -0.07
    opan
    -0.06
    æİ¥å¾ħ
    -0.06
    åįĥ人
    -0.06
    nect
    -0.06
     krauj
    -0.06
    rapid
    -0.06
    unan
    -0.06
    ashington
    -0.06
    POSITIVE LOGITS
     size
    0.05
    è¡¥ä¸ģ
    0.05
     laundry
    0.05
     rem
    0.05
    lings
    0.05
    åľ°
    0.05
     CPU
    0.04
     Reminder
    0.04
    _size
    0.04
    exec
    0.04
    Activations Density 0.010%

    No Known Activations