© 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. 3851
    Prev
    Next
    INDEX
    Explanations

    currently

    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
    æĽ¾
    -0.26
    æĽ¾ç»ı
    -0.25
    .recycle
    -0.23
    ä¹ŁæĽ¾
    -0.23
    ä»ĸæĽ¾
    -0.22
    æĽ¾åľ¨
    -0.21
    fabs
    -0.21
    åIJ¬è¯´è¿ĩ
    -0.21
    ä¸Ģ缴æĺ¯
    -0.20
    说è¿ĩ
    -0.20
    POSITIVE LOGITS
    æŃ£åľ¨
    0.33
     currently
    0.33
    æŃ£åľ¨è¿Ľè¡Į
    0.30
    çİ°è¡Į
    0.29
    Currently
    0.29
    æŃ£å¤Ħäºİ
    0.28
    çİ°çĬ¶
    0.28
     Currently
    0.28
    tdown
    0.27
    :black
    0.27
    Activations Density 0.215%

    No Known Activations