© 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. 1266
    Prev
    Next
    INDEX
    Explanations

    good quality

    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
    )throws
    -0.28
    çīĪæĿĥå½Ĵ
    -0.23
    ,void
    -0.20
    اعتÙħ
    -0.20
    ä¸Ģç·Ĵ
    -0.20
    urement
    -0.20
    setChecked
    -0.20
    obierno
    -0.19
    qing
    -0.19
     ?><
    -0.19
    POSITIVE LOGITS
    -quality
    0.31
    åĻĺ
    0.27
     (*)(
    0.26
    åĵģè´¨
    0.26
    "value
    0.26
    OrFail
    0.24
    æĹ¶æľº
    0.24
    åĹ«
    0.24
     quality
    0.23
    quality
    0.23
    Activations Density 2.497%

    No Known Activations