© 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. 45678
    Prev
    Next
    INDEX
    Explanations

    steps or stages

    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
     Porno
    -0.24
    oubted
    -0.23
    patible
    -0.22
    insula
    -0.21
    á»ĩp
    -0.21
    agascar
    -0.21
    chestra
    -0.20
    quate
    -0.20
     sublic
    -0.20
    åĸŁ
    -0.20
    POSITIVE LOGITS
    }elseif
    0.23
    å±¾
    0.22
    åŀ²
    0.21
    ?>↵↵↵
    0.20
    æŁ¥çľĭ详æĥħ
    0.20
    .executeQuery
    0.20
    ä¸ĭéĿ¢æĺ¯å°ı
    0.19
    idUser
    0.19
    è°¡
    0.19
    pres
    0.19
    Activations Density 0.006%

    No Known Activations