© 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. 925
    Prev
    Next
    INDEX
    Explanations

    technical parameters

    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
    ellites
    -0.24
     HOWEVER
    -0.24
    istani
    -0.24
    “
    -0.20
    rightness
    -0.20
     "
    -0.20
    HeaderText
    -0.20
    è¡®
    -0.19
     nowrap
    -0.19
    vasion
    -0.19
    POSITIVE LOGITS
     manh
    0.29
    æĪķ
    0.28
     fkk
    0.27
    *)((
    0.25
     oko
    0.24
    /effects
    0.23
    .Gravity
    0.23
    ï¼Ħ
    0.23
     newcom
    0.23
    çī¹åĪ«å£°æĺİ
    0.23
    Activations Density 11.869%

    No Known Activations