© 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. 2130
    Prev
    Next
    INDEX
    Explanations

    Titles or list items

    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
    .mybatisplus
    -0.21
    åķģ
    -0.21
    ''↵
    -0.20
    ToFit
    -0.20
    ä»ħä¾Ľ
    -0.19
    имв
    -0.19
    uxtap
    -0.18
    responsive
    -0.18
    鸦
    -0.18
    æļ¨
    -0.18
    POSITIVE LOGITS
    éĵŁ
    0.21
    räg
    0.21
    woord
    0.20
    oriously
    0.20
    iterals
    0.19
    ."'
    0.19
     canadian
    0.19
    ickerView
    0.18
    curacy
    0.18
    åķŃ
    0.18
    Activations Density 0.003%

    No Known Activations