© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 4077
    Prev
    Next
    INDEX
    Explanations

    and

    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
    aylight
    -0.28
    aeda
    -0.25
    .BASELINE
    -0.24
    steder
    -0.24
    âĺī
    -0.23
    ******č↵
    -0.23
    .Spring
    -0.21
    (textBox
    -0.21
    brtc
    -0.21
    Ź
    -0.21
    POSITIVE LOGITS
     beÄŁen
    0.21
    æľŁ
    0.21
    ãĤĴè¡ĮãģĦ
    0.20
     which
    0.18
     Ipsum
    0.17
    ·»
    0.17
    åįģä¸īå±Ĭ
    0.17
    åĮĸ
    0.17
     coast
    0.17
    ReactDOM
    0.17
    Activations Density 0.152%

    No Known Activations