© 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. 3784
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    /Dk
    -0.26
    )(((
    -0.25
    exels
    -0.24
    .createObject
    -0.22
    .charCodeAt
    -0.22
    )view
    -0.22
    [vertex
    -0.22
    eeper
    -0.22
    )new
    -0.21
    MMdd
    -0.21
    POSITIVE LOGITS
    è¹ĩ
    0.22
     csak
    0.19
    cr
    0.18
    ensively
    0.18
     pavement
    0.18
     Immutable
    0.18
     Nurs
    0.18
     Incre
    0.18
    edelta
    0.18
    íģ°
    0.18
    Activations Density 0.001%

    No Known Activations