© 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. 1510
    Prev
    Next
    INDEX
    Explanations

    size

    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
    IntervalSince
    -0.21
     dumpsters
    -0.21
    .TabIndex
    -0.21
    .authenticate
    -0.21
    æĽ´ä½İ
    -0.20
    åĪĨ彩
    -0.20
    ﹩
    -0.19
    IFE
    -0.19
     meilleur
    -0.19
     lowes
    -0.18
    POSITIVE LOGITS
     size
    0.60
    size
    0.49
    尺寸
    0.47
     sizes
    0.47
    大å°ı
    0.46
     length
    0.44
    éķ¿åº¦
    0.44
     Size
    0.43
    _size
    0.43
    Size
    0.43
    Activations Density 2.895%

    No Known Activations