© 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. 21764
    Prev
    Next
    INDEX
    Explanations

    all the

    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
    полне
    -0.06
    ger
    -0.06
    ×Ļ×Ŀ
    -0.06
    iski
    -0.06
    оби
    -0.06
    å¸ĮæľĽèĥ½å¤Łå¸®åĬ©
    -0.06
    ikos
    -0.06
    idas
    -0.06
    ulação
    -0.05
    esome
    -0.05
    POSITIVE LOGITS
    a
    0.06
    对äºĨ
    0.06
    ìĦľ
    0.06
    ÑİÑĤ
    0.06
    auch
    0.06
    o
    0.06
    å¬
    0.06
     buurt
    0.06
    aar
    0.05
    æľīåħ³äºİ
    0.05
    Activations Density 0.037%

    No Known Activations