© 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. 17879
    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
     trÃłng
    -0.06
     reflex
    -0.06
    èįī稿
    -0.06
    empel
    -0.06
    urg
    -0.06
    åŃ¦ä¹łæĢģ度
    -0.05
    imonio
    -0.05
    åħ¥åı£
    -0.05
    avra
    -0.05
     estim
    -0.05
    POSITIVE LOGITS
    оÑĢо
    0.06
    æĽ¼
    0.06
    eira
    0.06
    artige
    0.05
     ammessi
    0.05
     oluÅŁan
    0.05
    ä¸ĢæıIJ
    0.05
    udar
    0.05
    adis
    0.05
    åı¦ä¸Ģç§į
    0.05
    Activations Density 0.000%

    No Known Activations