© 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. 19218
    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
    çĢ
    -0.06
    æ¯ı
    -0.06
    s
    -0.05
    ang
    -0.05
    æĺ¾
    -0.05
    æľīæѤ
    -0.05
    ç²Ĺ
    -0.05
    Ñıз
    -0.05
     formed
    -0.05
    erma
    -0.04
    POSITIVE LOGITS
     Gins
    0.06
    zusetzen
    0.06
    zuführen
    0.06
    ÃīR
    0.06
    volv
    0.06
    好åĥı
    0.06
    polis
    0.06
    让ä¸ĸçķĮ
    0.06
    /documentation
    0.06
    uru
    0.06
    Activations Density 0.000%

    No Known Activations