© 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. 3110
    Prev
    Next
    INDEX
    Explanations

    body pain

    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
    onestly
    -0.24
    Soup
    -0.22
    BootApplication
    -0.22
    DMETHOD
    -0.22
    NameValuePair
    -0.21
    Cube
    -0.20
    仡
    -0.20
    YSTEM
    -0.19
    ondon
    -0.19
    .ERR
    -0.19
    POSITIVE LOGITS
    å±ģèĤ¡
    0.22
    ifestyles
    0.21
     sadd
    0.21
    èħ°éĥ¨
    0.21
    å¼Ģå°ģ
    0.21
     Karnataka
    0.21
     Newcastle
    0.21
     Pain
    0.21
    çĸ¼çĹĽ
    0.20
    szÄĻ
    0.20
    Activations Density 1.785%

    No Known Activations