© 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. 46066
    Prev
    Next
    INDEX
    Explanations

    setting AI persona

    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
    å¾ĹäºĨ
    -0.22
     Liebe
    -0.21
     frag
    -0.20
    .Typed
    -0.20
    ıld
    -0.18
    io
    -0.18
    ĸ
    -0.18
    appendChild
    -0.18
    ılm
    -0.18
    ç¼£
    -0.17
    POSITIVE LOGITS
     UNU
    0.22
    "crypto
    0.20
    说å®ŀ
    0.20
    ä¸ĬãģĮãģ£ãģ¦
    0.19
    -chief
    0.19
    ListAdapter
    0.19
     ×Ķ×ķ×ĵ
    0.18
    exact
    0.18
    ä¸ī大éĺ¶æ®µ
    0.18
    iffe
    0.18
    Activations Density 0.001%

    No Known Activations