© 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. 2763
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
    æĢĬ
    -0.25
     ());↵↵
    -0.24
    >Main
    -0.24
    CHA
    -0.23
    áºĴ
    -0.22
    AMILY
    -0.22
     (){
    -0.22
    ä¾®
    -0.22
    nage
    -0.21
    ÑĨиалÑĮн
    -0.21
    POSITIVE LOGITS
    æīĢåľ¨
    0.20
    son
    0.18
    gÅĤos
    0.18
     IDisposable
    0.18
    licken
    0.18
     linebacker
    0.18
     sophomore
    0.17
    ly
    0.17
     bloginfo
    0.17
    ese
    0.17
    Activations Density 0.001%

    No Known Activations