© 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. 18800
    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
    rie
    -0.06
    æĮº
    -0.05
    æ¦Ĩ
    -0.05
    å¹³æŶ
    -0.05
    bok
    -0.05
    ียว
    -0.05
    âĸ¡
    -0.04
    åı°æµ·
    -0.04
    colo
    -0.04
    iet
    -0.04
    POSITIVE LOGITS
     maggi
    0.06
    geg
    0.06
    影迷
    0.06
    ki
    0.06
    aip
    0.06
    صÙĬب
    0.06
    åĬŁäºİ
    0.06
    å°ĶåŁº
    0.06
     Listener
    0.06
    £¼
    0.06
    Activations Density 0.000%

    No Known Activations