© 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. 46682
    Prev
    Next
    INDEX
    Explanations

    you can

    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
     our
    -0.25
    æĪij们çļĦ
    -0.24
    our
    -0.23
    _hashes
    -0.21
     cores
    -0.21
    clusão
    -0.20
    illisecond
    -0.20
     ourselves
    -0.19
    å½
    -0.19
    .drawRect
    -0.19
    POSITIVE LOGITS
     citiz
    0.23
    ìķŀ
    0.23
     ?>↵↵↵
    0.23
    :host
    0.23
     Mourinho
    0.22
    QRST
    0.20
     volunte
    0.20
     activeClassName
    0.20
    pend
    0.20
    urances
    0.20
    Activations Density 0.054%

    No Known Activations