© 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. 20222
    Prev
    Next
    INDEX
    Explanations

    conference

    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
    igas
    -0.07
    è´¨çļĦ
    -0.06
    aksanakan
    -0.06
    èĥ¡åIJĮ
    -0.06
    uations
    -0.06
    à¸Ħà¹īาà¸Ļ
    -0.06
    fully
    -0.06
    кнÑĥ
    -0.06
    schirm
    -0.06
    mates
    -0.06
    POSITIVE LOGITS
    esh
    0.07
    à±į
    0.06
    PRI
    0.06
    esa
    0.06
    esi
    0.06
    ailles
    0.05
    ä¸įåĨ³
    0.05
    èĢ»
    0.05
    er
    0.05
    ingkatan
    0.05
    Activations Density 0.016%

    No Known Activations