© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21859
    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
     Pace
    -0.06
     (âĢ¦)
    -0.05
    éĤ£æŶ
    -0.05
    زاء
    -0.05
     Bytes
    -0.05
    çļĦéĺ¶æ®µ
    -0.05
     [âĢ¦
    -0.05
    wise
    -0.05
    лаÑĤ
    -0.05
    éĤ£å°±
    -0.05
    POSITIVE LOGITS
    unner
    0.06
    bedo
    0.05
    åѦåı²
    0.05
    æĺ¯åIJ¦ç¬¦åIJĪ
    0.05
    ä¸įå¾Ĺä½İäºİ
    0.05
    obot
    0.05
    ãģ³
    0.05
    mentos
    0.05
    formerly
    0.05
    okin
    0.05
    Activations Density 0.000%

    No Known Activations