© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19441
    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
     regarding
    -0.05
     towards
    -0.05
    ezz
    -0.05
    æł¹æ·±
    -0.05
    upid
    -0.05
    odynam
    -0.04
     Regarding
    -0.04
    æľīå¿ĥ
    -0.04
    аÑĨи
    -0.04
    è´¢
    -0.04
    POSITIVE LOGITS
    å·²å®Įç»ĵ
    0.07
     невÑĭ
    0.06
    èĦ
    0.06
    lius
    0.06
    дне
    0.06
    大åĸĿ
    0.06
    _then
    0.06
     komplette
    0.06
    .Xr
    0.06
    å¥Ĺ件
    0.06
    Activations Density 0.000%

    No Known Activations