© 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. 2331
    Prev
    Next
    INDEX
    Explanations

    medical scientific topics

    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
     pä
    -0.24
    'options
    -0.24
     Venezuel
    -0.20
     Shorts
    -0.20
    ansi
    -0.20
     indeb
    -0.19
    ãĢĤwww
    -0.19
    _nama
    -0.19
    被èªī
    -0.19
     strikeouts
    -0.18
    POSITIVE LOGITS
    lke
    0.21
    LOUR
    0.20
    ä¸įå°ijäºİ
    0.20
    ioc
    0.20
    grily
    0.20
    ↵				↵
    0.19
    aroo
    0.19
     captions
    0.19
    orWhere
    0.19
    kos
    0.19
    Activations Density 0.002%

    No Known Activations