© 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. 16580
    Prev
    Next
    INDEX
    Explanations

    programming code keywords

    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
    å¥ı
    -0.06
    estand
    -0.06
    ±
    -0.06
    èĩ
    -0.06
    misc
    -0.06
    å§
    -0.05
    ãĥŁãĥ¼
    -0.05
    üe
    -0.05
    ளி
    -0.05
    èĦĤ
    -0.05
    POSITIVE LOGITS
    à¹īว
    0.06
    exam
    0.06
    顺
    0.05
    alit
    0.05
     huyá»ģn
    0.05
    har
    0.05
    çµIJè«ĸ
    0.05
    aur
    0.05
    ĩ´
    0.05
    éłĨ
    0.05
    Activations Density 0.013%

    No Known Activations