© 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. 3533
    Prev
    Next
    INDEX
    Explanations

    true/false

    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
     {\↵
    -0.28
     ×Ķ×ķ×ĵ
    -0.27
     "[%
    -0.25
     baiser
    -0.25
     Bedrooms
    -0.24
    女æĢ§æľĭåıĭ
    -0.24
    æĿĪ
    -0.24
    />.
    -0.23
    æ»ļçIJĥ
    -0.23
    -mf
    -0.23
    POSITIVE LOGITS
    .Fat
    0.28
    çĬĴ
    0.24
    @update
    0.23
    .getOutputStream
    0.23
    (parseFloat
    0.23
    "default
    0.22
    .errorMessage
    0.22
    enticated
    0.21
    (describing
    0.21
    ï¼ļ"+
    0.21
    Activations Density 0.056%

    No Known Activations