© 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. 46208
    Prev
    Next
    INDEX
    Explanations

    legality

    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
    -Shirt
    -0.22
    ecided
    -0.22
    engeance
    -0.21
    ãİŀ
    -0.20
    BootApplication
    -0.19
    èŀĪ
    -0.19
    Vectorizer
    -0.19
     NotImplementedException
    -0.18
    STANCE
    -0.18
     Controlled
    -0.18
    POSITIVE LOGITS
    åIJĪæ³ķ
    0.39
    åIJĪæ³ķæĢ§
    0.32
    æĿĥéĻIJ
    0.28
    æľīæĿĥ
    0.28
     legality
    0.28
     lawful
    0.25
     legally
    0.25
    );}↵↵
    0.24
     authority
    0.23
     legal
    0.22
    Activations Density 0.083%

    No Known Activations