© 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. 19265
    Prev
    Next
    INDEX
    Explanations

    foreign language titles and names

    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
    oves
    -0.06
    istrate
    -0.06
     im
    -0.06
    uala
    -0.05
     []).
    -0.05
     mắt
    -0.05
     intuit
    -0.05
    resti
    -0.05
     intu
    -0.05
    sste
    -0.05
    POSITIVE LOGITS
    hyp
    0.06
    aisen
    0.06
    æĢ§å¼º
    0.06
    é«ĺå¯Ĩ
    0.05
    accion
    0.05
    weg
    0.05
    åIJ¬è¯Ŀ
    0.05
    æĪĸå°ij
    0.05
    ORTH
    0.05
    elde
    0.05
    Activations Density 0.008%

    No Known Activations