© 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. 3218
    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
     pathMatch
    -0.22
    .struts
    -0.20
    å·¥ä½ľæĬ¥åijĬ
    -0.19
    :]:↵
    -0.19
    ä¸Ģ大
    -0.18
    æĮĤ
    -0.17
    'value
    -0.17
    å®īæ£Ģ
    -0.17
     didSelectRowAtIndexPath
    -0.17
     ${({
    -0.17
    POSITIVE LOGITS
     menn
    0.23
     ná»Ļ
    0.21
    ceased
    0.21
    благо
    0.21
    iffany
    0.21
     Bowman
    0.20
    vê
    0.20
    éħļ
    0.20
    ëijł
    0.19
    indsight
    0.19
    Activations Density 0.000%

    No Known Activations