© 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. 18337
    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
     remot
    -0.06
    iddles
    -0.05
    ä¸ĥ大
    -0.05
    æĺ¾èĢĮæĺĵ
    -0.05
    软åĮĸ
    -0.05
     ÄIJông
    -0.05
    ç½ijä¸ĬçļĦ
    -0.05
    زع
    -0.05
    HM
    -0.05
    icali
    -0.05
    POSITIVE LOGITS
     enough
    0.06
    hung
    0.05
     Bro
    0.05
    äºĨ
    0.05
    ling
    0.05
    ÑĤи
    0.05
     synth
    0.05
    бÑĢан
    0.05
    bro
    0.05
    çļĦåIJĪæĪIJ
    0.05
    Activations Density 0.000%

    No Known Activations