© 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. 46803
    Prev
    Next
    INDEX
    Explanations

    full

    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
    Not in Any Lists

    No Comments

    Negative Logits
    (){}↵↵
    -0.24
    ↵↵
    -0.23
    Mahon
    -0.23
    "h
    -0.22
    PED
    -0.22
    sty
    -0.21
    (){}↵
    -0.21
    .§
    -0.21
    'u
    -0.21
     entire
    -0.21
    POSITIVE LOGITS
     enthus
    0.29
     hubby
    0.28
    опÑĢеделен
    0.25
    Indented
    0.24
     libertine
    0.24
     Interracial
    0.24
    hape
    0.23
     Unsure
    0.23
     DataService
    0.23
     thugs
    0.23
    Activations Density 0.018%

    No Known Activations