© 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. 18088
    Prev
    Next
    INDEX
    Explanations

    automobile, seeds, slave, dough, pulmonary, fixtures

    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
    eral
    -0.07
    ä¹ĭèĬ±
    -0.06
    AuthService
    -0.06
    edas
    -0.06
    uations
    -0.06
    çľ¼çľĭ
    -0.06
    kbd
    -0.06
    emento
    -0.06
     Eras
    -0.06
    æĸ¹å¼ıæĺ¯
    -0.06
    POSITIVE LOGITS
    æĮĩåIJij
    0.05
    avers
    0.05
    åĩ¡
    0.05
    set
    0.05
    re
    0.05
    eter
    0.05
    otec
    0.05
    èµ°å¼±
    0.05
    ä¸Ģ个个
    0.05
    normal
    0.05
    Activations Density 0.007%

    No Known Activations