© 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. 2624
    Prev
    Next
    INDEX
    Explanations

    exposure

    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
    SCRI
    -0.24
    ('@/
    -0.24
    é¾ĩ
    -0.22
    è·
    -0.22
    WARDED
    -0.21
    TXT
    -0.20
    IPHER
    -0.20
    è¿ĶåĽŀæIJľçĭIJ
    -0.20
    ãİı
    -0.20
    ç½ijåıĭè¯Ħ论
    -0.20
    POSITIVE LOGITS
    Exposed
    0.31
    eneg
    0.29
     exposure
    0.29
    æļ´éľ²
    0.29
     exposed
    0.29
    oard
    0.28
    elfast
    0.28
     expose
    0.27
    anoia
    0.27
    urrenc
    0.27
    Activations Density 0.055%

    No Known Activations