© 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. 17698
    Prev
    Next
    INDEX
    Explanations

    color and light exposure

    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
    éĻ£
    -0.05
    帮ä»ĸ
    -0.05
    äºĨ解èĩªå·±çļĦ
    -0.05
    cen
    -0.05
    娴
    -0.05
    à¹Ħà¸Ĺ
    -0.05
    éħįç½®æĸ¹éĿ¢
    -0.05
    Nova
    -0.05
    åĪ°ä»ĸ
    -0.05
    大æľī
    -0.05
    POSITIVE LOGITS
    messer
    0.07
    venuto
    0.06
    ey
    0.06
    enÃŃ
    0.05
     reten
    0.05
    åĮħä½ı
    0.05
    imana
    0.05
    eluar
    0.05
    ç£ħ
    0.05
    гла
    0.05
    Activations Density 0.014%

    No Known Activations