© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1079
    Prev
    Next
    INDEX
    Explanations

    symbols and junk

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/qwen2.5-7B-it-layer-20-saes/pile/matryoshka/k-100
    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
    abra
    -0.23
    bilder
    -0.20
    ç¥Ĺ
    -0.19
     trebuie
    -0.19
     adverts
    -0.19
    	HRESULT
    -0.19
    ulings
    -0.18
    getSingleton
    -0.18
    GV
    -0.18
    ascade
    -0.18
    POSITIVE LOGITS
     ============================================================================↵
    0.24
     Leban
    0.23
    étude
    0.23
    UNET
    0.23
    /GPL
    0.21
    зÑĭк
    0.21
    æıIJä¾Ľä¼ĺè´¨
    0.20
    ILLISECONDS
    0.20
    æĿ¨æ¬¢
    0.20
    @show
    0.19
    Activations Density 0.003%

    No Known Activations