© 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. 2092
    Prev
    Next
    INDEX
    Explanations

    placing something

    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
    -Methods
    -0.25
    ẹ
    -0.23
    Tambah
    -0.22
     Sunderland
    -0.21
    ıyla
    -0.21
    extérieur
    -0.21
    -caret
    -0.21
    -<?
    -0.20
    _THAT
    -0.20
    ijn
    -0.20
    POSITIVE LOGITS
    èIJľ
    0.23
    éĩįå¿ĥ
    0.23
    cstdint
    0.20
    æĸ°çļĦä¸Ģ
    0.20
    #echo
    0.20
     blame
    0.19
    注æĦıåĬĽ
    0.19
     onto
    0.19
    QDebug
    0.19
    ç²¾åĬĽ
    0.19
    Activations Density 0.679%

    No Known Activations