© 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-65K
    7. 2754
    Prev
    Next
    INDEX
    Explanations

    HIV virus

    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/pile/matryoshka/k-100
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĽĢ
    -0.25
     removeFromSuperview
    -0.20
    /kernel
    -0.19
     Xiaomi
    -0.19
     alignSelf
    -0.19
    ().'/
    -0.19
     Moines
    -0.19
     layui
    -0.19
    ulerAngles
    -0.18
    CHA
    -0.18
    POSITIVE LOGITS
    PGA
    0.26
    orgeous
    0.25
     HIV
    0.22
    å²·
    0.21
    .epam
    0.21
    ç¼Ĩ
    0.20
    åįĹéĿŀ
    0.20
     Polo
    0.19
    jure
    0.19
    _transaksi
    0.19
    Activations Density 1.279%

    No Known Activations