© 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. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 217
    Prev
    Next
    INDEX
    Explanations

    be

    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
     not
    -0.38
    not
    -0.35
     now
    -0.32
     being
    -0.29
     likely
    -0.28
     often
    -0.28
    now
    -0.28
     already
    -0.27
    .not
    -0.26
     still
    -0.26
    POSITIVE LOGITS
    acons
    0.38
    COME
    0.33
    friend
    0.31
    fall
    0.29
    ($('
    0.25
    przed
    0.25
    auty
    0.24
    tó
    0.23
    herits
    0.23
    ynchronously
    0.23
    Activations Density 1.106%

    No Known Activations