© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19898
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    añ
    -0.05
    éĥĬ
    -0.05
     L
    -0.05
    LI
    -0.05
    RIC
    -0.05
    O
    -0.05
    é¡¹çĽ®
    -0.05
    ä¸ĢçŃī
    -0.05
    åĿı
    -0.05
     with
    -0.05
    POSITIVE LOGITS
    æŀ¶ä¸Ĭ
    0.07
    à¸ķà¹Īà¸Ńà¸ģาร
    0.06
     alred
    0.06
    sms
    0.06
    oho
    0.06
    éģĵéģĵ
    0.06
     utk
    0.06
    èµ°ä¸ĭåİ»
    0.06
    nTo
    0.06
    æĪIJç«ł
    0.06
    Activations Density 0.000%

    No Known Activations