© 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. 2761
    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
     (![
    -0.21
    körper
    -0.21
     indeb
    -0.21
    .Args
    -0.21
    :"-
    -0.20
    инÑĤеÑĢеÑģ
    -0.20
    ether
    -0.20
    !=(
    -0.19
    -syntax
    -0.19
    specialchars
    -0.19
    POSITIVE LOGITS
    avigate
    0.24
    rael
    0.21
    åľ¨ä¸Ģ
    0.20
     acknow
    0.20
    åıįé¦Ī
    0.19
     CascadeType
    0.19
    /details
    0.18
    اط
    0.18
     sorter
    0.17
    èľī
    0.17
    Activations Density 0.001%

    No Known Activations