© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 573
    Prev
    Next
    INDEX
    Explanations

    code or technical terms

    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
    i
    -0.29
     démarch
    -0.29
    l
    -0.28
    chedulers
    -0.28
    e
    -0.28
    تسÙħ
    -0.27
    o
    -0.26
    /disable
    -0.25
    u
    -0.25
    r
    -0.25
    POSITIVE LOGITS
    /Dk
    0.25
    ouston
    0.23
    -notch
    0.23
    imenti
    0.23
    ä¼ĹæīĢåij¨
    0.21
    çĹĺçĹĺ
    0.21
    ropri
    0.21
    viewController
    0.21
    诩
    0.20
     )↵↵↵↵↵↵↵↵
    0.20
    Activations Density 4.443%

    No Known Activations