© 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. 3481
    Prev
    Next
    INDEX
    Explanations

    past tense endings

    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
    .Middle
    -0.20
    _refresh
    -0.20
    ças
    -0.19
    æĿ¨
    -0.19
     NDEBUG
    -0.19
    ORTH
    -0.19
    :"-"`↵
    -0.18
    å°ıæŶåīį
    -0.18
    _Tick
    -0.18
    .getRuntime
    -0.18
    POSITIVE LOGITS
     ×Ķ×ķ×ĵ
    0.26
    zee
    0.23
    picable
    0.22
    à¸ĭะ
    0.21
    ]")]↵
    0.21
    .openConnection
    0.21
    iless
    0.21
     søger
    0.21
    åĪ©çĶ¨æĤ¨çļĦ
    0.21
    !!");↵
    0.20
    Activations Density 0.586%

    No Known Activations