© 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. 2404
    Prev
    Next
    INDEX
    Explanations

    Programming code

    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
     Nude
    -0.22
     Clips
    -0.21
    @SpringBootTest
    -0.21
    )index
    -0.20
    pons
    -0.19
    .setViewport
    -0.19
    uely
    -0.19
    aised
    -0.19
    姱
    -0.18
    ipsis
    -0.18
    POSITIVE LOGITS
    ="__
    0.23
     ActionController
    0.20
    lineEdit
    0.19
     onPostExecute
    0.19
    (QStringLiteral
    0.19
    女æĢ§æľĭåıĭ
    0.19
    ë°ĸ
    0.19
    ":"/
    0.19
    Substring
    0.18
    UGC
    0.18
    Activations Density 0.001%

    No Known Activations