© 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. 46454
    Prev
    Next
    INDEX
    Explanations

    access codes

    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
    JOR
    -0.22
    celand
    -0.21
    ForResult
    -0.21
    ominated
    -0.21
     '../../../../../
    -0.20
    éĤĭ
    -0.19
     {?>↵
    -0.19
    ={"/
    -0.19
    houette
    -0.18
    setBackground
    -0.18
    POSITIVE LOGITS
    iferay
    0.25
    -caret
    0.22
    utas
    0.20
    ặp
    0.20
    ILLISE
    0.20
    满足
    0.19
    -serving
    0.19
     Powell
    0.19
    à¹Ĥà¸Ļ
    0.19
    quat
    0.19
    Activations Density 0.002%

    No Known Activations