© 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. 19036
    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
    ä¼Ĭæĸ¯
    -0.06
    æľīæīĢ
    -0.05
    orman
    -0.05
     THEN
    -0.05
    羣æŃ£
    -0.05
    ught
    -0.05
    idup
    -0.05
    ereal
    -0.05
    ouro
    -0.05
    Ø«ÙĨ
    -0.05
    POSITIVE LOGITS
    зн
    0.06
    waard
    0.06
    été
    0.06
    Ñıн
    0.06
    zyw
    0.06
     cál
    0.06
    usu
    0.06
    æŁĶç¾İ
    0.06
    voi
    0.06
    olik
    0.06
    Activations Density 0.000%

    No Known Activations