© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2254
    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
    ;left
    -0.23
    imbledon
    -0.22
    иÑĢÑĥÑİÑī
    -0.21
    :"#
    -0.19
    CDATA
    -0.19
    Benchmark
    -0.19
    OUNTRY
    -0.18
    ;top
    -0.18
     ÑĢаÑģÑģказÑĭва
    -0.18
    EFR
    -0.18
    POSITIVE LOGITS
    è¹Ń
    0.21
    estar
    0.19
    инÑĤеÑĢеÑģ
    0.19
    .','
    0.19
    Mathf
    0.19
    lrt
    0.19
     ör
    0.18
    baseUrl
    0.18
    ủng
    0.18
     adoles
    0.18
    Activations Density 0.001%

    No Known Activations