© 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. 1575
    Prev
    Next
    INDEX
    Explanations

    above/previous sections

    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
     èĭ¥è¦ģ
    -0.27
     practition
    -0.27
     Publié
    -0.24
     élè
    -0.23
    )arg
    -0.23
     incons
    -0.23
    ĵĺ
    -0.22
    â¼¥
    -0.22
     Posté
    -0.21
     yarg
    -0.21
    POSITIVE LOGITS
     above
    0.50
     earlier
    0.47
     previous
    0.45
    åīįéĿ¢
    0.43
    ä¸ĬéĿ¢
    0.42
    åīįè¿°
    0.42
     вÑĭÑĪе
    0.41
     section
    0.38
    above
    0.37
    ä¸Ĭè¿°
    0.36
    Activations Density 0.795%

    No Known Activations