© 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. 18988
    Prev
    Next
    INDEX
    Explanations

    reflected in

    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
    ç´
    -0.06
    è¿ĻäºĽåĽłç´ł
    -0.05
    åĴĮæıIJåįĩ
    -0.05
    astian
    -0.05
    åľ¨åŃ¦ä¹łä¸Ĭ
    -0.05
    зеÑĢ
    -0.05
    éĻ
    -0.05
     dish
    -0.05
    zez
    -0.05
     via
    -0.05
    POSITIVE LOGITS
    бÑĥдÑĮ
    0.06
    dav
    0.05
    å¾·åĪ©
    0.05
    à¸Ĺีà¹Ģà¸Ķียว
    0.05
    åŃ¦å£«
    0.05
     استÙĤباÙĦ
    0.05
    ä¸Ĭ人
    0.05
    ording
    0.05
    ç©«
    0.05
    jam
    0.05
    Activations Density 0.013%

    No Known Activations