© 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. 264
    Prev
    Next
    INDEX
    Explanations

    code related snippets

    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
     GANG
    -0.25
     LATIN
    -0.23
     numel
    -0.23
     thuis
    -0.21
     scarc
    -0.21
    "crypto
    -0.21
     }):
    -0.21
    ãĢĤãĢĮ
    -0.20
    ä¸ĭéĿ¢æĺ¯å°ı
    -0.20
    -Sah
    -0.20
    POSITIVE LOGITS
    :CGRect
    0.29
    :params
    0.24
    =$("#
    0.23
    udiant
    0.22
    ighbor
    0.22
    /]
    0.22
    âĦħ
    0.22
    ?>/
    0.21
    .moveToNext
    0.21
    <=$
    0.21
    Activations Density 1.681%

    No Known Activations