© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 1448
    Prev
    Next
    INDEX
    Explanations

    numbers and scientific notation

    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
    aternity
    -0.25
    angler
    -0.23
    claimer
    -0.23
    UILDER
    -0.23
    uncan
    -0.22
    ocrates
    -0.22
    edics
    -0.22
    iage
    -0.22
    .setToolTipText
    -0.22
    @Web
    -0.22
    POSITIVE LOGITS
    ceipt
    0.23
    *>&
    0.21
    levelname
    0.19
    erg
    0.19
    åıįèħIJåĢ¡å»ī
    0.19
     Ple
    0.19
    .IsNullOrWhiteSpace
    0.18
     Bench
    0.18
    BUF
    0.18
    ught
    0.18
    Activations Density 0.117%

    No Known Activations