© 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. 3903
    Prev
    Next
    INDEX
    Explanations

    event

    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
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.24
    <=(
    -0.22
    ÃľR
    -0.21
    .Promise
    -0.20
    Century
    -0.19
    (dy
    -0.19
    noteq
    -0.19
     fair
    -0.19
    mouseleave
    -0.19
    kek
    -0.18
    POSITIVE LOGITS
    äºĭ件
    0.27
    -events
    0.25
    -event
    0.24
    malink
    0.24
    event
    0.24
     event
    0.23
    laps
    0.23
    åıijçĶŁ
    0.23
     EVENTS
    0.22
     svenska
    0.22
    Activations Density 0.131%

    No Known Activations