© 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. 2968
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     cerco
    -0.25
    )throws
    -0.22
    å¿ħä¸įåı¯
    -0.20
    éĥ¨åī¯
    -0.20
    rador
    -0.19
    OPLE
    -0.19
     equalTo
    -0.19
    ÂŃt
    -0.19
     Noticed
    -0.19
    æīĢæīĢéķ¿
    -0.18
    POSITIVE LOGITS
    ëħĶ
    0.21
    "@
    0.20
    )index
    0.20
    =wx
    0.19
    CHEDULE
    0.19
     Guzzle
    0.19
    )init
    0.19
    anitize
    0.18
    æĪĸèĢħ说
    0.18
    ATUS
    0.18
    Activations Density 0.327%

    No Known Activations