© 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. 1960
    Prev
    Next
    INDEX
    Explanations

    s words

    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
    ãģĵãģ¨
    -0.35
    alyzed
    -0.28
    icaid
    -0.28
    isclosed
    -0.28
    влеÑĩен
    -0.27
    gether
    -0.26
    prech
    -0.25
     ×Ķ×ķ×ĵ
    -0.25
    olicited
    -0.25
    -cols
    -0.24
    POSITIVE LOGITS
    s
    1.08
    ×Ļ×Ŀ
    0.40
    sheets
    0.36
    ments
    0.35
    sar
    0.35
    sburg
    0.35
    sand
    0.34
    äºĨ
    0.33
    sword
    0.32
    som
    0.32
    Activations Density 10.692%

    No Known Activations