© 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. 18549
    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
    olit
    -0.07
    æĮ¯
    -0.06
     Vil
    -0.06
    å¡ĺéķĩ
    -0.06
    ssa
    -0.06
     soucis
    -0.06
    ular
    -0.06
     Resta
    -0.06
    æ¯ħ
    -0.06
    old
    -0.06
    POSITIVE LOGITS
     indef
    0.05
    amkan
    0.05
    主é¢ĺåħļæĹ¥æ´»åĬ¨
    0.05
    Ñĥв
    0.05
     results
    0.05
    åĽ¾æĸ¯
    0.05
    ...
    0.05
    arian
    0.05
    anii
    0.05
    Master
    0.05
    Activations Density 0.000%

    No Known Activations