© 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. 1777
    Prev
    Next
    INDEX
    Explanations

    situation or issue

    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
    -Semit
    -0.28
    .rmi
    -0.27
    "';
    -0.23
    []>↵
    -0.22
    byss
    -0.21
    .StartPosition
    -0.21
    =").
    -0.20
    ustralian
    -0.20
    cff
    -0.20
    WillAppear
    -0.20
    POSITIVE LOGITS
    äºĨ好åĩł
    0.24
    :checked
    0.24
    个交æĺĵ
    0.23
    éħĬ
    0.23
    activex
    0.22
    饴
    0.21
    (s
    0.21
    á»ģm
    0.21
    gambar
    0.20
    bulan
    0.20
    Activations Density 5.743%

    No Known Activations