© 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. 20675
    Prev
    Next
    INDEX
    Explanations

    flying and soaring

    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
    太éĩį
    -0.05
    é¢Ŀå¤ĸ
    -0.05
     Heavy
    -0.05
    enso
    -0.05
    模åĿĹ
    -0.05
    اÙĤØ©
    -0.05
    æĬĺåıł
    -0.05
     favor
    -0.05
    laz
    -0.05
    asse
    -0.05
    POSITIVE LOGITS
    å¢ĥçķĮ
    0.07
    翱ç¿Ķ
    0.06
    ÑģÑĤеÑģÑĤвенно
    0.06
    ovich
    0.06
    idy
    0.06
    reet
    0.06
    æºħ
    0.06
    junk
    0.06
    .microsoft
    0.06
    å·¡åĽŀ
    0.06
    Activations Density 0.015%

    No Known Activations