© 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. 17558
    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
    åIJĽ
    -0.06
    åIJ«ä¹ī
    -0.05
    endah
    -0.05
     encoded
    -0.05
    gaard
    -0.05
    compressed
    -0.05
    èķ´åIJ«
    -0.05
    ido
    -0.05
    æİīçļĦ
    -0.05
    irez
    -0.05
    POSITIVE LOGITS
    etak
    0.07
    æľīä¸ĭåĪĹ
    0.07
    ä¸Ńéķ¿æľŁ
    0.06
    æľīçĶŁ
    0.06
    bs
    0.06
    icks
    0.06
    éģĵåħī
    0.06
    éĢĤçĶ¨æ³ķå¾ĭ
    0.05
    tridges
    0.05
    ä¸ĢåĪĩ
    0.05
    Activations Density 0.000%

    No Known Activations