© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-CHAT-65K
    7. 45462
    Prev
    Next
    INDEX
    Explanations

    understand

    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/lmsys/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 192 tokens each
    Dataset (Dashboard)
    chanind/lmsys-chat-1m-qwen-2.5
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    []{↵
    -0.25
    tingham
    -0.25
    rvine
    -0.25
    ENCED
    -0.24
    ISMATCH
    -0.23
    |;↵
    -0.22
    (/^\
    -0.22
    )((((
    -0.22
    -exc
    -0.21
    ignKey
    -0.21
    POSITIVE LOGITS
    为ä»Ģä¹Ī
    0.25
     why
    0.24
    为ä»Ģä¹Īä¸į
    0.24
    为ä»Ģä¹Īè¦ģ
    0.24
    为ä»Ģä¹Īä¼ļ
    0.23
    èŀħ
    0.22
    Why
    0.22
    Disappear
    0.21
    为ä½ķ
    0.21
     Why
    0.21
    Activations Density 0.020%

    No Known Activations