© 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. 21831
    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
    çŃł
    -0.06
    burgh
    -0.06
     dun
    -0.05
    кеÑĤ
    -0.05
     either
    -0.05
    -class
    -0.05
     effective
    -0.05
    ²
    -0.05
    icum
    -0.04
    )['
    -0.04
    POSITIVE LOGITS
     Gond
    0.06
     ÑĥÑĩе
    0.06
    lac
    0.06
    erp
    0.06
    è¿Ļ个è¿ĩç¨ĭ
    0.06
     Condic
    0.06
    зÑĭ
    0.06
    nü
    0.06
    acs
    0.06
    prep
    0.06
    Activations Density 0.000%

    No Known Activations