© 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. 19321
    Prev
    Next
    INDEX
    Explanations

    usage: instruction

    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
    æĭįåĩº
    -0.06
    mitt
    -0.06
     won
    -0.05
     suite
    -0.05
     rong
    -0.05
    ждÑĥÑİ
    -0.05
    osed
    -0.05
    éĢļè¿ĩ对
    -0.05
     Suh
    -0.05
    true
    -0.05
    POSITIVE LOGITS
    imy
    0.06
    éºĹ
    0.06
    mentions
    0.06
    ÛĮدÛĮ
    0.05
    opard
    0.05
    羨
    0.05
    ::
    0.05
    丽
    0.05
    ķ
    0.05
    atories
    0.05
    Activations Density 0.001%

    No Known Activations