© 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. 3509
    Prev
    Next
    INDEX
    Explanations

    programming terms

    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
    _HALF
    -0.21
     [&](
    -0.19
    éķ¯
    -0.18
    妪
    -0.18
    pyx
    -0.18
    #line
    -0.18
    деÑĢжан
    -0.18
    è´¸æĺĵæĪĺ
    -0.18
    ulan
    -0.18
    ìķĬ
    -0.18
    POSITIVE LOGITS
    Ủ
    0.23
    -expanded
    0.22
     eskort
    0.22
    dzi
    0.22
    )size
    0.21
    :CGRect
    0.21
     createState
    0.21
    reshape
    0.21
    MMdd
    0.20
    á¾±
    0.20
    Activations Density 0.060%

    No Known Activations