© 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. 20832
    Prev
    Next
    INDEX
    Explanations

    tens digit

    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
    æѤ
    -0.05
    å¾Ļ
    -0.05
    еÑħ
    -0.05
    ibat
    -0.05
    %X
    -0.05
    ãģ³
    -0.05
    Aws
    -0.05
    -env
    -0.05
    ä¸įæĺİ
    -0.05
    ead
    -0.05
    POSITIVE LOGITS
    stek
    0.06
    ulary
    0.06
    æĸ¯å¡Ķ
    0.06
    jeni
    0.06
     particular
    0.05
    دÙħ
    0.05
    uther
    0.05
    artial
    0.05
    æĺŃ
    0.05
     slate
    0.05
    Activations Density 0.001%

    No Known Activations