© 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. 2023
    Prev
    Next
    INDEX
    Explanations

    say "("

    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
    (requestCode
    -0.29
    (confirm
    -0.28
    (DBG
    -0.27
    (userData
    -0.26
    (dateTime
    -0.26
    (StringUtils
    -0.25
    ($('<
    -0.25
    (ErrorMessage
    -0.25
    (currentUser
    -0.25
    çݩ家æĿ¥è¯´
    -0.25
    POSITIVE LOGITS
     (
    1.06
    ï¼Ī
    0.81
     ï¼Ī
    0.70
    (
    0.64
     (↵
    0.57
     (č↵
    0.51
     ('
    0.51
     (`
    0.50
     ("
    0.50
     (_
    0.49
    Activations Density 8.393%

    No Known Activations