© 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. 17799
    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
    æŁı
    -0.06
    iss
    -0.05
    athan
    -0.05
    ç§ijåѦåѦéĻ¢
    -0.05
    landes
    -0.05
    è§Ĥä¼Ĺ们
    -0.05
    isy
    -0.05
    们对
    -0.05
     SEA
    -0.05
    æ³ķè¦ı
    -0.05
    POSITIVE LOGITS
     whole
    0.06
    æĹ¥æ´»åĬ¨
    0.06
     ÙĪØ°
    0.06
    åħ³å¿ĥçļĦéĹ®é¢ĺ
    0.06
    å¼Ģåı£
    0.05
    árom
    0.05
    èĮĥæĸĩ
    0.05
    arian
    0.05
    iform
    0.05
    OOT
    0.05
    Activations Density 0.000%

    No Known Activations