© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 922
    Prev
    Next
    INDEX
    Explanations

    legal terms

    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
    âļĹ
    -0.25
    娣
    -0.22
    /../
    -0.21
    aggable
    -0.21
    ält
    -0.20
    (Have
    -0.20
    âĮĤ
    -0.20
    resizing
    -0.20
    ÐIJвÑĤо
    -0.20
    .onStart
    -0.20
    POSITIVE LOGITS
     sublicense
    0.28
     INTERRUPTION
    0.28
     NONINFRINGEMENT
    0.26
     DISCLAIMED
    0.26
     ADVISED
    0.25
     Redistributions
    0.25
     SUBSTITUTE
    0.25
     FITNESS
    0.24
    KHTML
    0.24
     PROCUREMENT
    0.23
    Activations Density 2.601%

    No Known Activations