© 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. 1565
    Prev
    Next
    INDEX
    Explanations

    numerical range

    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
     aver
    -0.21
    ing
    -0.20
    ↵
    -0.20
     cul
    -0.19
    uiten
    -0.19
    èĩªè§ī
    -0.19
    s
    -0.19
    æĸĩåĪĽ
    -0.18
     plur
    -0.18
    çļĦåŃĺåľ¨
    -0.18
    POSITIVE LOGITS
    __;
    0.30
     èĭ¥è¦ģ
    0.23
     !=↵
    0.23
    naments
    0.23
    âĺİ
    0.23
    âľķ
    0.23
    忽
    0.23
     çĶŁåij½åij¨æľŁ
    0.22
    :;↵
    0.22
    hế
    0.22
    Activations Density 0.054%

    No Known Activations