© 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. 3629
    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
    Ê·
    -0.22
    puties
    -0.21
    çĭŀ
    -0.21
    imulator
    -0.20
    ï¹¢
    -0.20
    bsub
    -0.20
    untime
    -0.19
    ']=="
    -0.19
    ernals
    -0.19
     bordel
    -0.19
    POSITIVE LOGITS
    (DBG
    0.22
    	mysqli
    0.21
    QRST
    0.20
    macen
    0.20
    >())
    0.20
     BRE
    0.20
    ')."
    0.19
    -describedby
    0.19
    ]={↵
    0.19
    翳
    0.19
    Activations Density 0.000%

    No Known Activations