© 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. 530
    Prev
    Next
    INDEX
    Explanations

    country names

    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
    avanaugh
    -0.21
    ëĮIJ
    -0.20
     milano
    -0.19
    occan
    -0.19
    -Methods
    -0.19
    ispiel
    -0.19
    onents
    -0.19
     nieu
    -0.19
    idot
    -0.19
     pBuffer
    -0.18
    POSITIVE LOGITS
     USA
    0.33
    USA
    0.25
     GLsizei
    0.24
    ippines
    0.21
    ITA
    0.20
    ///<
    0.20
     (~(
    0.20
    -caption
    0.19
     Salah
    0.19
    åħµ
    0.19
    Activations Density 1.937%

    No Known Activations