© 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. 18058
    Prev
    Next
    INDEX
    Explanations

    publication and release events

    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
    ä»İä»Ĭå¹´
    -0.06
     sector
    -0.06
    ä»İåݻ年
    -0.06
    ลึà¸ģ
    -0.05
    Ñĥг
    -0.05
    itorium
    -0.05
     recent
    -0.05
    latest
    -0.05
    Sector
    -0.05
     recently
    -0.05
    POSITIVE LOGITS
    ä¸įä¸Ĭ
    0.06
    rebro
    0.05
    æ·ĭ
    0.05
    à¸Ĺาà¸ĩà¸ģาร
    0.05
    çļĦç¥ŀæĥħ
    0.05
     Mech
    0.05
    .createObject
    0.05
    æĹłéĺ»
    0.05
    sale
    0.05
    æĹłå¼Ĥè®®
    0.05
    Activations Density 0.178%

    No Known Activations