© 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. 2134
    Prev
    Next
    INDEX
    Explanations

    is

    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
     means
    -0.22
    orizontal
    -0.22
     todd
    -0.20
    ette
    -0.20
    ìĻľ
    -0.20
    ange
    -0.19
     itself
    -0.19
    âĺ°
    -0.19
    .presenter
    -0.19
    achsen
    -0.19
    POSITIVE LOGITS
    achable
    0.21
    puty
    0.20
    称ä¹ĭ
    0.19
    ä¸įæĺ¯ä¸Ģ个
    0.19
    ==(
    0.19
    enment
    0.19
    ulary
    0.19
    Erreur
    0.19
    绾
    0.18
    !=(
    0.18
    Activations Density 0.228%

    No Known Activations