© 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. 3332
    Prev
    Next
    INDEX
    Explanations

    code or jargon

    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
    .Footer
    -0.22
    .KeyCode
    -0.21
    å®°
    -0.21
    åħ¨èµĦåŃIJ
    -0.21
    _queues
    -0.20
     strtol
    -0.19
    uml
    -0.19
    ᾶ
    -0.19
    .ObjectModel
    -0.19
    ç»Ī端
    -0.19
    POSITIVE LOGITS
    .MouseAdapter
    0.26
    imagin
    0.19
     März
    0.19
    elen
    0.19
    ESA
    0.19
    -await
    0.19
    .opend
    0.19
     bergen
    0.19
    ä¸Ľä¹¦
    0.18
     FITNESS
    0.18
    Activations Density 0.002%

    No Known Activations