© 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. 1966
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    å¿ħä¸įåı¯
    -0.28
    ä»İæł¹æľ¬
    -0.24
    éĶ¦æłĩ
    -0.23
    ite
    -0.22
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.21
    毫æĹłçĸij
    -0.21
    istani
    -0.20
     intéressant
    -0.20
    SSION
    -0.20
    åĭł
    -0.20
    POSITIVE LOGITS
     CircularProgress
    0.27
    -validate
    0.25
    logan
    0.24
    <=$
    0.24
    ryo
    0.22
    WidgetItem
    0.22
    -www
    0.22
    ubre
    0.22
    leanor
    0.22
    <quote
    0.21
    Activations Density 0.439%

    No Known Activations