© 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. 45969
    Prev
    Next
    INDEX
    Explanations

    si

    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
    ilmington
    -0.29
    âļĹ
    -0.28
     prostit
    -0.28
    [".
    -0.28
    esteem
    -0.27
    .'_
    -0.26
    thinkable
    -0.26
     cuckold
    -0.26
    .SetParent
    -0.25
    '=>['
    -0.25
    POSITIVE LOGITS
     dumpsters
    0.36
     isempty
    0.26
     numel
    0.25
    è¹ģ
    0.24
     Necklace
    0.23
     Dresses
    0.23
    etter
    0.22
     fullfile
    0.22
     jMenuItem
    0.22
     Huckabee
    0.21
    Activations Density 0.009%

    No Known Activations