© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19565
    Prev
    Next
    INDEX
    Explanations

    spokesman or spokeswoman

    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
    ÑģÑĤеÑģÑĤвенно
    -0.07
    ört
    -0.06
    æľīæīĢæĢĿ
    -0.06
    pargne
    -0.06
    ://${
    -0.06
    erring
    -0.06
    ays
    -0.05
    ühren
    -0.05
    erras
    -0.05
    orsa
    -0.05
    POSITIVE LOGITS
    æł¸
    0.05
    ç¾½
    0.05
    ycl
    0.05
    èĶ¼
    0.05
    ãĥĨãĥ¼ãĤ¸
    0.05
    lint
    0.05
    ↵
    0.05
     giunta
    0.05
     sano
    0.05
     event
    0.05
    Activations Density 0.030%

    No Known Activations