© 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. 20631
    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
    à¹Ģà¸Ńà¸ĩ
    -0.05
    åħ³äºİ
    -0.05
    angs
    -0.05
     necessarily
    -0.05
    ohlen
    -0.05
    åĽłä¸ºæĺ¯
    -0.05
     unless
    -0.05
     Dir
    -0.05
    ava
    -0.05
    个
    -0.05
    POSITIVE LOGITS
    çģ¿
    0.07
     odw
    0.06
    åĴĮ丰å¯ĮçļĦ
    0.06
    彩å¦Ĩ
    0.06
    çģ«çº¿
    0.06
    illard
    0.06
    éĿŀ常满æĦı
    0.06
    izzard
    0.06
    åı¯éĢī
    0.05
    大ä¸Ń
    0.05
    Activations Density 0.000%

    No Known Activations