© 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. 3054
    Prev
    Next
    INDEX
    Explanations

    code or technical

    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
    olvency
    -0.24
     Parenthood
    -0.23
    forcements
    -0.21
     strSql
    -0.20
    zyst
    -0.20
     '<%=
    -0.20
    ares
    -0.20
    <=$
    -0.20
    ’all
    -0.19
    ASHBOARD
    -0.18
    POSITIVE LOGITS
    éĥ¨åī¯
    0.23
    ();)
    0.22
     getenv
    0.21
    :numel
    0.19
    Bat
    0.19
    Mech
    0.19
    åłª
    0.18
    аблиÑĨ
    0.18
     timespec
    0.18
    bourne
    0.18
    Activations Density 0.001%

    No Known Activations