© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 810
    Prev
    Next
    INDEX
    Explanations

    reason

    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
     Millenn
    -0.26
    AsyncResult
    -0.24
    initializer
    -0.24
     Dems
    -0.23
    ipheral
    -0.23
    âĪİ
    -0.23
    Prostit
    -0.23
     déco
    -0.23
     Parenthood
    -0.23
     maté
    -0.23
    POSITIVE LOGITS
     why
    0.42
     reasons
    0.36
    为ä»Ģä¹Ī
    0.34
     reason
    0.34
    Why
    0.33
     Why
    0.33
     Reasons
    0.32
    why
    0.32
    ä»Ģä¹ĪåİŁåĽł
    0.29
    为ä»Ģä¹Īè¦ģ
    0.28
    Activations Density 1.874%

    No Known Activations