© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 2135
    Prev
    Next
    INDEX
    Explanations

    specific 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
    RenderTarget
    -0.21
    ReadStream
    -0.21
    handleRequest
    -0.19
    AGMA
    -0.19
    IPP
    -0.19
    )(__
    -0.18
     misd
    -0.18
    èµħ
    -0.18
    ictionaries
    -0.18
    emet
    -0.18
    POSITIVE LOGITS
     huis
    0.21
     Duis
    0.20
    (',',$
    0.20
     arg
    0.20
    haus
    0.20
     Enlight
    0.19
    ;"><?
    0.19
     '".$
    0.18
    .putExtra
    0.18
     bbw
    0.18
    Activations Density 0.006%

    No Known Activations