© 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. 17788
    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
    ChangeEvent
    -0.06
    çİĩé«ĺ
    -0.06
    çŀ¬æģ¯
    -0.06
    bine
    -0.05
    raits
    -0.05
     Ø¢ÛĮÙĨدÙĩ
    -0.05
    æŁ³
    -0.05
     recorr
    -0.05
     unknown
    -0.05
    icine
    -0.05
    POSITIVE LOGITS
     mú
    0.06
    æ¤į
    0.06
    åĨ
    0.05
    sj
    0.05
    æī®
    0.05
    ented
    0.05
    åİĭåĻ¨
    0.05
    æĺ¯åIJĹ
    0.05
    scheduled
    0.05
    稿
    0.05
    Activations Density 0.000%

    No Known Activations