© 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. 21392
    Prev
    Next
    INDEX
    Explanations

    comments enclosing code

    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
    aub
    -0.05
     Rendez
    -0.05
     C
    -0.05
    âĢ
    -0.05
    æĺ¯ä¸Ģé¢Ĺ
    -0.05
     ë
    -0.05
    jas
    -0.05
    ipped
    -0.05
    C
    -0.05
     evolved
    -0.05
    POSITIVE LOGITS
    undry
    0.06
    ERENCE
    0.06
    liš
    0.06
    æłª
    0.06
    leistung
    0.06
    åķĨå®ļ
    0.06
    ë¥ĺ
    0.06
     vaid
    0.06
    lech
    0.06
    æı´
    0.06
    Activations Density 0.001%

    No Known Activations