© 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. 20223
    Prev
    Next
    INDEX
    Explanations

    mathematical variables or expressions

    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
     *–
    -0.06
    è®°åĪĨ
    -0.06
    ging
    -0.06
    à¹Ģลยà¹Į
    -0.06
    å¿łå®ŀ
    -0.06
    æľīåģ¿
    -0.05
    ienne
    -0.05
    estet
    -0.05
    ð
    -0.05
    å½¼
    -0.05
    POSITIVE LOGITS
    undra
    0.06
     Schneider
    0.06
    wall
    0.05
    urus
    0.05
    orry
    0.05
    veda
    0.05
    prite
    0.05
     cómod
    0.05
    .mozilla
    0.05
     individual
    0.05
    Activations Density 0.056%

    No Known Activations