© 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. 20106
    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
    ijin
    -0.07
    bine
    -0.06
    mere
    -0.06
    æºIJçļĦ
    -0.06
    ÛĮرÛĮ
    -0.06
     annet
    -0.06
    egen
    -0.06
    å¼ĵ
    -0.06
    çºĸ
    -0.06
    绣
    -0.05
    POSITIVE LOGITS
    大æľī
    0.06
     fak
    0.06
    å±ķå¼Ģåħ¨æĸĩ
    0.05
    uas
    0.05
     rh
    0.05
    æľīæĿ¡ä»¶
    0.05
    ans
    0.05
    å°Ĩå°±
    0.05
    ok
    0.05
    æķĻç§ij
    0.05
    Activations Density 0.000%

    No Known Activations