© 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. 46170
    Prev
    Next
    INDEX
    Explanations

    numerical data

    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
    çıº
    -0.25
     (!!
    -0.23
    <decltype
    -0.21
    éĨ
    -0.20
     awakeFromNib
    -0.20
     propName
    -0.20
    åĮºåŁŁåĨħ
    -0.20
    Nd
    -0.19
     under
    -0.19
    jourd
    -0.19
    POSITIVE LOGITS
    etak
    0.26
    ÙħÙĪضÙĪع
    0.26
     fkk
    0.26
    >'.↵
    0.24
    å§ĭ建
    0.24
    .fm
    0.23
    .heroku
    0.22
    éviter
    0.22
    :update
    0.22
    ?action
    0.21
    Activations Density 0.002%

    No Known Activations