© 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. 46282
    Prev
    Next
    INDEX
    Explanations

    role playing

    np_max-act-logits · gemini-2.5-flash-lite

    Finds explicit persona or role-assignment tokens that label or set the assistant's character/name in the conversation.

    oai_token-act-pair · gpt-5-miniTriggered by @msahalmulki
    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
    AMILY
    -0.24
    æŁ¥çľĭ详æĥħ
    -0.22
    RIEND
    -0.22
    _gettime
    -0.21
    ystack
    -0.21
    .SingleOrDefault
    -0.20
    .OrderByDescending
    -0.20
    ulfill
    -0.19
     cellForRowAt
    -0.19
     Cloth
    -0.19
    POSITIVE LOGITS
    tingham
    0.22
    è¿Ļæĺ¯ä¸Ģ个
    0.21
     CircularProgress
    0.21
    ListComponent
    0.21
    -semibold
    0.20
    ?>↵↵↵
    0.20
     strugg
    0.19
    ILA
    0.19
    libft
    0.19
    incinnati
    0.19
    Activations Density 0.088%

    No Known Activations