© 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. 19934
    Prev
    Next
    INDEX
    Explanations

    urologists

    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
    urai
    -0.06
    ogl
    -0.06
    alore
    -0.06
     Subs
    -0.05
    Blan
    -0.05
    èĢ³çĽ®
    -0.05
    ä¸įçģŃ
    -0.05
    agenzia
    -0.05
    æīĺ
    -0.05
    ä¸Ģ件
    -0.05
    POSITIVE LOGITS
    ä¸įè§ģ
    0.06
    emaan
    0.06
    OST
    0.05
     Beverly
    0.05
    æĺ¥é£İ
    0.05
    ä¸įåĪ°çļĦ
    0.05
    kev
    0.05
    ¤
    0.05
    ost
    0.05
    è¦ģæ±Ĥ被åijĬ
    0.05
    Activations Density 0.017%

    No Known Activations