© 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. 21585
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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
    æľī礼
    -0.06
     بÙĨÙĬ
    -0.06
    http
    -0.05
    æľīåĬŁ
    -0.05
    anas
    -0.05
    ista
    -0.05
    en
    -0.05
    aso
    -0.05
    åĮ
    -0.05
     purposes
    -0.05
    POSITIVE LOGITS
    unsch
    0.06
    tring
    0.05
    еÑĩа
    0.05
    longleftrightarrow
    0.05
    paged
    0.05
    æĸ¹çļĦ
    0.05
    cÃŃ
    0.05
    æĢĿæĥ³å·¥ä½ľ
    0.05
     Kö
    0.05
    å±İ
    0.05
    Activations Density 0.027%

    No Known Activations