© 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. 2828
    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
     btnCancel
    -0.20
    ç©´
    -0.20
    åĢļ
    -0.19
     useContext
    -0.19
    ä½ĵ温
    -0.19
    -pills
    -0.18
    orWhere
    -0.18
     signatures
    -0.18
    ãĦĴ
    -0.18
    POSITIVE LOGITS
     AndAlso
    0.24
    .FileWriter
    0.23
    ндекÑģ
    0.23
    remium
    0.21
    ublisher
    0.20
    iband
    0.20
    cheid
    0.20
    arness
    0.20
    âĺķ
    0.19
    __);↵↵
    0.19
    Activations Density 0.000%

    No Known Activations