© 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. 3868
    Prev
    Next
    INDEX
    Explanations

    level

    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
     signings
    -0.23
     ma
    -0.22
    en
    -0.21
     asc
    -0.21
     cud
    -0.21
    rvine
    -0.21
     usu
    -0.20
     env
    -0.20
    .PER
    -0.20
     obs
    -0.20
    POSITIVE LOGITS
    oproject
    0.33
    ornment
    0.30
    Ĩ
    0.28
     difficolt
    0.27
     Prostit
    0.27
    resenter
    0.25
     Annunci
    0.25
     Noticed
    0.24
    Ỹ
    0.24
     LEVEL
    0.24
    Activations Density 0.076%

    No Known Activations