© 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. 3772
    Prev
    Next
    INDEX
    Explanations

    past learning

    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
     oko
    -0.29
    wchar
    -0.28
     Rosenstein
    -0.27
     McCart
    -0.26
     bied
    -0.26
     Kushner
    -0.25
     pomys
    -0.25
     jeste
    -0.24
     Maher
    -0.24
     zob
    -0.24
    POSITIVE LOGITS
    /Instruction
    0.35
     tatto
    0.34
     lucr
    0.32
    gnore
    0.31
    úb
    0.29
    éĵij
    0.28
     roma
    0.28
    /stretch
    0.28
    zimmer
    0.27
     intox
    0.27
    Activations Density 17.586%

    No Known Activations