© 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. 16783
    Prev
    Next
    INDEX
    Explanations

    main function argument `argv`

    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
     **—
    -0.07
    wäl
    -0.07
    åĭĩå¾Ģ缴åīį
    -0.07
    æĸ°åĬłåĿ¡
    -0.07
    leden
    -0.07
     Inde
    -0.07
    ovre
    -0.07
     Teixe
    -0.07
    inique
    -0.07
    TROS
    -0.07
    POSITIVE LOGITS
    /
    0.07
    ing
    0.06
    ster
    0.06
    v
    0.05
    ç
    0.05
    uk
    0.05
    V
    0.05
    太éĥİ
    0.05
    çī©
    0.05
    çī©çļĦ
    0.05
    Activations Density 0.004%

    No Known Activations