© 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. 17126
    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
    hend
    -0.06
    ä¸İåīį
    -0.05
    æľįçļĦ
    -0.05
    ä¸İå½ĵåľ°
    -0.05
    bourne
    -0.05
    лли
    -0.05
    ä¼ļåIJĮ
    -0.04
    为åħ¨åĽ½
    -0.04
    çĭ
    -0.04
    heb
    -0.04
    POSITIVE LOGITS
    eda
    0.08
    人åıĹ伤
    0.08
    earer
    0.07
    edin
    0.07
    åŃĺ
    0.06
    гоÑĤ
    0.06
    envoi
    0.06
    isspace
    0.06
    emblée
    0.06
    ียà¸ļ
    0.06
    Activations Density 0.000%

    No Known Activations