© 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. 21157
    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
    æ½ľ
    -0.07
    "."
    -0.06
     rivol
    -0.06
    tai
    -0.06
     wenden
    -0.06
     bak
    -0.06
    åĪł
    -0.06
    hend
    -0.06
     risal
    -0.06
    بد
    -0.06
    POSITIVE LOGITS
    èĥ¯
    0.05
    åıĸç·ł
    0.05
    å¾ĢæľŁç²¾å½©
    0.05
    æĬľ
    0.05
    ÏĢÏī
    0.05
     اÙĦعÙĦÙĬا
    0.05
    ÏĢε
    0.05
     said
    0.05
     okul
    0.05
    FontAwesome
    0.04
    Activations Density 0.000%

    No Known Activations