© 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. 3944
    Prev
    Next
    INDEX
    Explanations

    ordinal 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
    1
    -0.36
    åįĬæľĪ
    -0.19
    ä¸ĢçĻ¾
    -0.19
     sức
    -0.18
    achel
    -0.18
    Listener
    -0.17
    _SOCKET
    -0.17
    2
    -0.17
    etus
    -0.17
     mann
    -0.17
    POSITIVE LOGITS
     III
    0.36
     fourth
    0.35
    III
    0.32
    ç¬¬åĽĽ
    0.30
     third
    0.30
    ï¼ĵ
    0.30
     fifth
    0.29
    åĽĽäºĶ
    0.29
     Third
    0.29
    ä¸īåĽĽ
    0.29
    Activations Density 0.401%

    No Known Activations