© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 831
    Prev
    Next
    INDEX
    Explanations

    mathematical variables

    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
    orgeous
    -0.26
    >:</
    -0.20
    .Gradient
    -0.19
    èį£
    -0.19
    bulan
    -0.19
    =zeros
    -0.19
    .deepEqual
    -0.19
    .UUID
    -0.18
    gambar
    -0.18
    lish
    -0.18
    POSITIVE LOGITS
    forgettable
    0.30
    代表
    0.29
    æĺ¯æĮĩ
    0.27
    为代表
    0.25
     represents
    0.25
    æĺ¯çĶ¨æĿ¥
    0.25
    代表çĿĢ
    0.25
    åĪĻæĺ¯
    0.25
    æĮĩçļĦæĺ¯
    0.25
    çĶ¨æĿ¥
    0.24
    Activations Density 1.590%

    No Known Activations