© 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. 16703
    Prev
    Next
    INDEX
    Explanations

    nested structures in programming

    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
    nable
    -0.08
    elong
    -0.07
    äºļè¿IJ
    -0.06
    adiyah
    -0.06
    ampton
    -0.06
    empt
    -0.06
    é³Į
    -0.06
    Ñħодов
    -0.06
     puk
    -0.06
    -minded
    -0.06
    POSITIVE LOGITS
    ated
    0.07
    éĻIJäºİ
    0.06
    (
    0.05
     coincidence
    0.05
    us
    0.05
    most
    0.05
    åıį转
    0.05
    Prev
    0.05
    ATING
    0.05
     ones
    0.05
    Activations Density 0.012%

    No Known Activations