© 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. 46144
    Prev
    Next
    INDEX
    Explanations

    way

    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
    #ac
    -0.24
    ĥ
    -0.23
    ,");↵
    -0.22
    åħħåĪĨ
    -0.22
    loquent
    -0.21
    /Dk
    -0.20
    åĨħ马
    -0.20
    onestly
    -0.20
    Åĥ
    -0.20
    FINE
    -0.20
    POSITIVE LOGITS
    swire
    0.23
    resden
    0.23
    iferay
    0.22
    оÑĨен
    0.21
    .getHeight
    0.21
     RoundedRectangle
    0.21
     erfolgre
    0.21
    è¿ĩåİ»çļĦ
    0.20
    好çļĦ
    0.20
     AudioClip
    0.20
    Activations Density 0.009%

    No Known Activations