© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3203
    Prev
    Next
    INDEX
    Explanations

    topics and introductions

    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
     pragma
    -0.21
    å¿Ŀ
    -0.19
    ]={
    -0.18
    åħ¶ä½Ļ
    -0.18
    itory
    -0.18
    æ©ĩ
    -0.18
     hack
    -0.18
    æĪį
    -0.18
     ÑģÑĤоÑĢо
    -0.17
    robe
    -0.17
    POSITIVE LOGITS
     MatSnackBar
    0.22
    parseFloat
    0.22
    .EventQueue
    0.20
    VERTISEMENT
    0.19
     POLIT
    0.19
    uncture
    0.19
     overwhel
    0.19
    ä½ij
    0.19
    agnar
    0.19
    (parseFloat
    0.19
    Activations Density 0.001%

    No Known Activations