© 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. 18664
    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
     univers
    -0.06
    åİ»çľĭçľĭ
    -0.05
    icht
    -0.05
    éĸĵ
    -0.05
    venture
    -0.05
     giác
    -0.05
    å¤Ħ女
    -0.05
    éĹ´çļĦ
    -0.05
     visual
    -0.05
    uis
    -0.05
    POSITIVE LOGITS
    åIJ¦åĪĻ
    0.06
     sekalipun
    0.06
     Otherwise
    0.06
    åIJ¦åīĩ
    0.06
    imd
    0.06
     battu
    0.06
    ÙĬÙĭا
    0.06
     otherwise
    0.06
     altrimenti
    0.06
     whatsoever
    0.05
    Activations Density 0.000%

    No Known Activations