© 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. 19978
    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
    wich
    -0.07
    egis
    -0.06
    秦çİĭ
    -0.06
    awai
    -0.06
    æľĭåħĭ
    -0.05
    paring
    -0.05
     gian
    -0.05
    AMAN
    -0.05
    ÑĦек
    -0.05
     Tuk
    -0.05
    POSITIVE LOGITS
    inst
    0.06
    ellen
    0.06
    enn
    0.05
     hope
    0.05
     Te
    0.05
    alent
    0.05
    elle
    0.05
    tes
    0.05
     rate
    0.05
     gain
    0.05
    Activations Density 0.000%

    No Known Activations