© 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. 19307
    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
    åľĺ
    -0.05
    åıĬ个人
    -0.05
    IOR
    -0.05
     اÙĦشر
    -0.05
    ANDOM
    -0.05
    auty
    -0.05
    -org
    -0.05
    ä¸į许
    -0.05
     exec
    -0.05
    åĸĦ
    -0.05
    POSITIVE LOGITS
    æĺİä¿¡
    0.06
    æĸĩæķĻ
    0.06
    zend
    0.06
    ading
    0.06
    illé
    0.06
    laz
    0.06
    antie
    0.06
    ç½®
    0.06
    ohen
    0.05
    adic
    0.05
    Activations Density 0.000%

    No Known Activations