© 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. 3759
    Prev
    Next
    INDEX
    Explanations

    technical terms and symbols

    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
    #ga
    -0.23
    ileaks
    -0.23
    lassian
    -0.22
    åħ¨åĬĽä»¥
    -0.22
    uers
    -0.22
     Nutzung
    -0.21
    -Sah
    -0.21
     Åļw
    -0.21
    rarian
    -0.21
     авг
    -0.21
    POSITIVE LOGITS
    .KeyPress
    0.20
    éĢĥ
    0.20
     guilt
    0.20
    nonnull
    0.19
    ('.'
    0.19
    æĢĿ
    0.18
    _iters
    0.18
    rg
    0.18
    zik
    0.18
     olmad
    0.18
    Activations Density 0.001%

    No Known Activations