© 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. 3465
    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
    });↵↵↵↵
    -0.24
    "title
    -0.24
    ámara
    -0.23
    âĦī
    -0.23
     çĶŁåij½åij¨æľŁ
    -0.21
    RTOS
    -0.21
    IRTUAL
    -0.21
     =>'
    -0.20
    /Internal
    -0.20
     ucwords
    -0.20
    POSITIVE LOGITS
    aguay
    0.21
    广
    0.21
    >>&
    0.19
    rest
    0.19
     :\
    0.18
    çĽĤ
    0.18
    esda
    0.18
    zipcode
    0.18
     rest
    0.18
    uar
    0.18
    Activations Density 0.000%

    No Known Activations