© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-CHAT-65K
    7. 45657
    Prev
    Next
    INDEX
    Explanations

    code and technical text

    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
    Negative Logits
    ubbo
    -0.28
    娣
    -0.25
    /↵↵↵↵
    -0.24
    edback
    -0.24
     (;;)
    -0.23
    overe
    -0.23
    болезн
    -0.23
    linky
    -0.22
    vertisement
    -0.22
    WithEmail
    -0.22
    POSITIVE LOGITS
    ä½ĵèĤ²æĬķ注
    0.23
     jadx
    0.21
     ragazze
    0.21
    >Loading
    0.21
    linkplain
    0.20
     ifdef
    0.20
    ysqli
    0.20
    åĴĮæĶ¯æĮģ
    0.20
    IJľ
    0.19
    vil
    0.19
    Activations Density 0.717%

    No Known Activations