© 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. 22015
    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
    MLE
    -0.06
     Downs
    -0.06
    çݯèĬĤçļĦ
    -0.06
    DSA
    -0.06
     Ful
    -0.06
    åĽ½åįİ
    -0.06
    æģ©
    -0.06
     cáo
    -0.06
    asma
    -0.06
     кÑĢай
    -0.05
    POSITIVE LOGITS
    erez
    0.06
    atur
    0.06
    obody
    0.06
    amanya
    0.05
     amazed
    0.05
    æ´ĭ
    0.05
    arth
    0.05
    ervação
    0.05
    isiv
    0.05
    curity
    0.05
    Activations Density 0.000%

    No Known Activations