© 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. 18754
    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
    asc
    -0.06
    ÑĢа
    -0.06
    atan
    -0.06
    天
    -0.05
     berb
    -0.05
    elic
    -0.05
    ün
    -0.05
    ban
    -0.05
    бай
    -0.05
    à¸Ń
    -0.05
    POSITIVE LOGITS
    uco
    0.06
    æĪĸ个人
    0.05
    cach
    0.05
    æĪĸ缺
    0.05
     Selle
    0.05
     تØŃ
    0.05
    dern
    0.05
    mach
    0.05
    æ³¥
    0.05
    æĪĸ被
    0.05
    Activations Density 0.000%

    No Known Activations