© 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. 3571
    Prev
    Next
    INDEX
    Explanations

    Request

    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
    noinspection
    -0.27
    vertisement
    -0.25
    abyrin
    -0.24
    iêu
    -0.24
     treff
    -0.24
    ukkit
    -0.23
     Erot
    -0.22
     (![
    -0.22
    >({
    -0.22
    iferay
    -0.22
    POSITIVE LOGITS
    AnimationFrame
    0.24
     请æ±Ĥ
    0.23
     onFocus
    0.21
     onAnimation
    0.20
     deselect
    0.18
     componentDidUpdate
    0.18
    è·»
    0.18
     kullanılan
    0.18
     onTouch
    0.18
    LLL
    0.17
    Activations Density 0.060%

    No Known Activations