© 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. 17403
    Prev
    Next
    INDEX
    Explanations

    json objects

    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
    ÙħÙĴ
    -0.06
     béné
    -0.06
    解
    -0.05
    为å¸Ī
    -0.05
    tests
    -0.05
    çŁ¥çļĦ
    -0.05
     Weise
    -0.05
    nyi
    -0.05
     nao
    -0.05
    rest
    -0.05
    POSITIVE LOGITS
    mitt
    0.06
    iewicz
    0.06
    agement
    0.05
    éz
    0.05
     quin
    0.05
    ãģ¥ãģı
    0.05
    à¹Ģà¸Ľà¹ĩà¸Ļà¸Ńยà¹Īาà¸ĩ
    0.05
    aim
    0.05
    uage
    0.05
    åħģ
    0.05
    Activations Density 0.023%

    No Known Activations