© 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. 46377
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
    .RegisterType
    -0.21
    ÙħعÙĦÙĪÙħات
    -0.20
    [at
    -0.20
    .putText
    -0.19
    conditionally
    -0.19
     Oversight
    -0.18
    ä¸įçĦ¶
    -0.18
     NOTHING
    -0.18
    UGHT
    -0.18
    _txn
    -0.18
    POSITIVE LOGITS
    <fieldset
    0.21
     ApplicationException
    0.21
    intendent
    0.21
     tonumber
    0.21
     './../../
    0.20
    GES
    0.19
    COORD
    0.19
     verv
    0.19
     menj
    0.19
     móc
    0.19
    Activations Density 0.101%

    No Known Activations