© 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. 18199
    Prev
    Next
    INDEX
    Explanations

    textile products and industry

    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
    éĩı
    -0.07
    escu
    -0.07
    orto
    -0.07
    rece
    -0.07
    spre
    -0.06
    мÑĥÑĢ
    -0.06
     nostalg
    -0.06
    æĶ¶
    -0.06
    estand
    -0.06
    缴
    -0.06
    POSITIVE LOGITS
    tures
    0.07
    ek
    0.07
    rite
    0.06
    ses
    0.06
    Ú¯ÛĮ
    0.06
    init
    0.05
    Ø·
    0.05
    atering
    0.05
    æĺł
    0.05
    tiny
    0.05
    Activations Density 0.001%

    No Known Activations