© 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-CHAT-65K
    7. 46471
    Prev
    Next
    INDEX
    Explanations

    code related terms

    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
     Bracket
    -0.23
     Während
    -0.19
    ä¸įæľį
    -0.19
     lineback
    -0.19
     airstrikes
    -0.18
    ãģĨãģĵãģ¨
    -0.18
    å´´
    -0.17
    .Contracts
    -0.17
    å«Į
    -0.17
    å±IJ
    -0.17
    POSITIVE LOGITS
     cuckold
    0.23
    -dismissible
    0.22
    illet
    0.21
    iliar
    0.21
    structuring
    0.20
    olds
    0.20
    imité
    0.20
    plen
    0.20
    -opacity
    0.20
    .Glide
    0.20
    Activations Density 0.003%

    No Known Activations