© 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. 18998
    Prev
    Next
    INDEX
    Explanations

    units digit, factor, multiple

    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
    æĬķåħ¥
    -0.06
    langs
    -0.06
    CLA
    -0.06
     Einschrän
    -0.06
    عÙħ
    -0.06
    æĬķ
    -0.06
     eten
    -0.06
    åį°
    -0.06
    /umd
    -0.06
    é«ĺ强
    -0.06
    POSITIVE LOGITS
    ida
    0.06
    bo
    0.06
    im
    0.06
    æĿĥ
    0.05
    ism
    0.05
    wh
    0.05
    om
    0.05
     dist
    0.05
    pd
    0.05
    Featured
    0.05
    Activations Density 0.003%

    No Known Activations