© 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. 474
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     ×Ķ×ķ×ĵ
    -0.29
     ÑģоÑĩеÑĤа
    -0.24
    >:</
    -0.23
    iá»ĩn
    -0.23
    ederland
    -0.22
    Ḳ
    -0.21
    usercontent
    -0.21
    oÄŁ
    -0.21
    åħļé£İ
    -0.20
    gregar
    -0.20
    POSITIVE LOGITS
     which
    0.68
    which
    0.64
     whose
    0.51
     коÑĤоÑĢÑĭй
    0.43
    Which
    0.42
    whose
    0.41
     Which
    0.40
     WHICH
    0.40
    .which
    0.39
     vá»ijn
    0.39
    Activations Density 2.887%

    No Known Activations