© 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. 21788
    Prev
    Next
    INDEX
    Explanations

    all

    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
    à¸Ħู
    -0.06
    æĸ°æľº
    -0.06
    çijĻ
    -0.06
     inf
    -0.05
    çıŃ
    -0.05
    resher
    -0.05
    æĿ¨æŁ³
    -0.05
    ä¾Ŀæį®
    -0.05
    ä¸įçĿĢ
    -0.05
    éĵ
    -0.05
    POSITIVE LOGITS
    оÑģÑĤа
    0.07
     competit
    0.06
    ì¶ķ
    0.06
    wic
    0.06
    æĬ¢æĸŃ
    0.06
    erton
    0.06
     ná»ķi
    0.06
    ovol
    0.06
     blamed
    0.06
     Ortega
    0.06
    Activations Density 0.023%

    No Known Activations