© 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. 21866
    Prev
    Next
    INDEX
    Explanations

    command line arguments

    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
     Rai
    -0.06
    ãĥ©ãĥĸ
    -0.05
     progressive
    -0.05
    对åIJĦç§į
    -0.05
    é¢ĺ为
    -0.05
    æĶ¯éĺŁä¼į
    -0.05
    ampa
    -0.05
     particular
    -0.05
    ä»Ģä¹Īéĥ½
    -0.05
    terms
    -0.05
    POSITIVE LOGITS
    onal
    0.06
    chow
    0.06
    omatis
    0.05
    ä¸Ģ审åĪ¤åĨ³
    0.05
    zet
    0.05
    chst
    0.05
    اتÛĮ
    0.05
    etter
    0.05
    deen
    0.05
    .API
    0.05
    Activations Density 0.010%

    No Known Activations