© 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. 3084
    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
    æĸ°åŀĭåĨł
    -0.28
    UCCESS
    -0.24
    uggage
    -0.24
    olib
    -0.23
     èĩªåĬ¨çĶŁæĪIJ
    -0.21
    âĹĤ
    -0.21
    skirts
    -0.21
     Pornhub
    -0.21
     beÄŁen
    -0.21
    ød
    -0.21
    POSITIVE LOGITS
    <decltype
    0.20
     union
    0.19
     macro
    0.19
    个çĻ¾åĪĨ
    0.19
    y
    0.19
     y
    0.19
    .redirect
    0.19
     v
    0.19
    ä»ĸå°±
    0.19
     contr
    0.19
    Activations Density 0.000%

    No Known Activations