© 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. 17010
    Prev
    Next
    INDEX
    Explanations

    appoint, Health, Create, Repair, wind, Profile, add, Live

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ebilecek
    -0.07
    apur
    -0.07
    åIJīæĢĿ
    -0.06
    éĹ´
    -0.06
    anders
    -0.06
    æİ
    -0.06
    <*
    -0.06
    -guard
    -0.06
    pur
    -0.06
    ssi
    -0.06
    POSITIVE LOGITS
    از
    0.05
    ÃĤ
    0.05
    azen
    0.05
    å·¥ä½ľå²Ĺä½į
    0.05
     perpendicular
    0.05
     perk
    0.05
    æĬĢæľ¯æĸ¹æ¡Ī
    0.05
     Wolf
    0.05
     diagnosed
    0.04
    LEY
    0.04
    Activations Density 0.006%

    No Known Activations