© 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. 46545
    Prev
    Next
    INDEX
    Explanations

    Yes/No confirmation

    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
    ç½ijç«Ļé¦ĸ页
    -0.23
    alchemy
    -0.22
    被èªī
    -0.21
    游æĪı代
    -0.21
    èĭĦ
    -0.21
    abcdefghijklmnop
    -0.20
    '].$
    -0.20
    _processes
    -0.19
    .IsNullOr
    -0.19
     Genç
    -0.19
    POSITIVE LOGITS
    maids
    0.21
    isty
    0.21
    )|(
    0.20
    ESSAGE
    0.20
    åĵī
    0.19
    -Regular
    0.19
     fatt
    0.19
     Everton
    0.19
    pegawai
    0.18
     acompaña
    0.18
    Activations Density 0.002%

    No Known Activations