© 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. 1204
    Prev
    Next
    INDEX
    Explanations

    court case numbers

    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
    è¶Ķ
    -0.23
    stdarg
    -0.22
    /tos
    -0.21
    ouncement
    -0.21
    éĵIJ
    -0.20
     Woche
    -0.20
    ThanOr
    -0.20
    ãİİ
    -0.20
    buat
    -0.19
    Ulus
    -0.19
    POSITIVE LOGITS
    ç¼ĸåı·
    0.30
    åŃĹ第
    0.29
     çĶŁåij½åij¨æľŁ
    0.23
    ä»ħ代表
    0.23
    (EFFECT
    0.23
    .Locale
    0.22
    åĿļå®ļä¸į
    0.22
    åı·
    0.21
     //~
    0.21
    èħ
    0.20
    Activations Density 1.598%

    No Known Activations