© 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. 21610
    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
    wsze
    -0.06
    æ½ľä¼ı
    -0.06
    æĭ¥æľīçĿĢ
    -0.06
    æĪijåĽ½ç»ıæµİ
    -0.05
    érate
    -0.05
    zysz
    -0.05
    ubil
    -0.05
    æĹłéĹ´
    -0.05
    arily
    -0.05
    aylor
    -0.05
    POSITIVE LOGITS
    oros
    0.06
    ries
    0.06
    ahan
    0.05
    iments
    0.05
    empel
    0.05
    iman
    0.05
    дови
    0.05
    rosa
    0.05
    æŃ£æĺ¯åľ¨
    0.05
    ç®ĢæŀIJ
    0.05
    Activations Density 0.000%

    No Known Activations