© 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. 2185
    Prev
    Next
    INDEX
    Explanations

    ratios

    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
    ëĪĶ
    -0.20
    à¸ĩาà¸Ļ
    -0.20
    .mount
    -0.20
     cur
    -0.18
    jax
    -0.18
    éĩĿ
    -0.18
    ystack
    -0.18
    ÙĪÙħ
    -0.17
     Eugene
    -0.17
     mw
    -0.17
    POSITIVE LOGITS
    åĢį
    0.35
     ratio
    0.30
     ratios
    0.28
     Ratio
    0.28
    Ratio
    0.28
    ratio
    0.26
    _ratio
    0.25
    æ¯Ķçİĩ
    0.22
    апÑĢимеÑĢ
    0.21
    åı
    0.21
    Activations Density 0.175%

    No Known Activations