© 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. 16688
    Prev
    Next
    INDEX
    Explanations

    numbers and units like px

    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
    аÑĤÑĭ
    -0.06
    ungi
    -0.05
     Bridges
    -0.05
    ãģĭãģª
    -0.05
    allis
    -0.05
    é»Ħæ²¹
    -0.05
    igs
    -0.05
    åĪĺ家
    -0.05
    ç¼ł
    -0.05
    åºĬ
    -0.05
    POSITIVE LOGITS
    tabil
    0.06
    tz
    0.06
    metic
    0.06
    天ä¸Ģ
    0.06
    s
    0.05
     Smy
    0.05
     Carm
    0.05
     frank
    0.05
    yata
    0.05
    lus
    0.05
    Activations Density 0.003%

    No Known Activations