© 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. 21217
    Prev
    Next
    INDEX
    Explanations

    code constructs including segments, types, or numerical data

    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
    ืà¹Īà¸Ń
    -0.06
     اÙĦتÙĤ
    -0.06
    éĺ¿
    -0.06
    åĴĮéĺ¿
    -0.06
    quist
    -0.06
    leck
    -0.06
    vim
    -0.06
    ding
    -0.06
    еÑĩи
    -0.06
    end
    -0.06
    POSITIVE LOGITS
    askan
    0.05
    åĽ½åĬ¡éĻ¢
    0.05
    æıļ
    0.05
    czyn
    0.05
    à¤ķरà¥į
    0.05
    æĪŁ
    0.05
     *\
    0.05
    ä»°
    0.05
     raised
    0.05
     hell
    0.05
    Activations Density 0.075%

    No Known Activations