© 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. 17435
    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
    جÙĦ
    -0.06
    geg
    -0.06
    erner
    -0.05
    (relative
    -0.05
    à¤Ĺà¥Ģ
    -0.05
    .newArrayList
    -0.05
     an
    -0.05
     Cascade
    -0.05
    è¥Ł
    -0.05
     anot
    -0.05
    POSITIVE LOGITS
     اÙĦدراسÙĬØ©
    0.06
    è¨ĢãģĦ
    0.06
     ÑĢодов
    0.06
    quier
    0.05
    è¯ĿæĿ¥
    0.05
    ommer
    0.05
     artistique
    0.05
     luck
    0.05
    ier
    0.05
    lore
    0.05
    Activations Density 0.000%

    No Known Activations