© 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. 17747
    Prev
    Next
    INDEX
    Explanations

    common abbreviations and subsequent words

    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
     st
    -0.06
     marg
    -0.06
    gar
    -0.05
     neither
    -0.05
    orm
    -0.05
    uge
    -0.05
    italia
    -0.05
    %\
    -0.05
     tr
    -0.05
     St
    -0.05
    POSITIVE LOGITS
     postan
    0.06
    鼨ä¸Ń
    0.06
    她äºĨ
    0.06
    ä½łäºĨ
    0.06
    asaran
    0.06
    ترز
    0.06
     internation
    0.06
    æŀĹéĢ¸
    0.06
    表示æĦŁè°¢
    0.06
     nih
    0.05
    Activations Density 0.004%

    No Known Activations