© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen2.5-7B-IT
    5. 20-MATRYOSHKA-65K
    7. 3657
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
    htag
    -0.24
     UICollectionViewCell
    -0.23
    pan
    -0.20
    rtl
    -0.19
    æŃ£åľ¨è¿Ľè¡Į
    -0.19
    èĻij
    -0.18
    NSBundle
    -0.18
    çķĮ第ä¸Ģ
    -0.18
    hip
    -0.18
    讲课
    -0.18
    POSITIVE LOGITS
     antibiot
    0.22
    gee
    0.22
     brun
    0.21
    ðŁĻĭ
    0.20
    kest
    0.19
    toISOString
    0.19
    CompatActivity
    0.18
    apgolly
    0.18
    dden
    0.18
    .GetResponse
    0.18
    Activations Density 0.001%

    No Known Activations