© 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. 2427
    Prev
    Next
    INDEX
    Explanations

    Technical code

    np_max-act-logits · gemini-2.5-flash-lite
    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
    .MouseAdapter
    -0.24
    .Magenta
    -0.23
    ()?>
    -0.21
    ëijł
    -0.20
    ãĤħ
    -0.19
    æݨèįIJéĺħ读
    -0.19
    rô
    -0.18
     ÑģÑĤоим
    -0.18
    æľĽçĿĢ
    -0.18
    ('').
    -0.18
    POSITIVE LOGITS
    CCCCCC
    0.20
    -Token
    0.20
    ıld
    0.20
    飬
    0.20
    jeta
    0.20
    atego
    0.20
    iÄħ
    0.19
    hotmail
    0.19
    ocache
    0.19
    æŶæĬ¥
    0.19
    Activations Density 0.002%

    No Known Activations