© 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. 2774
    Prev
    Next
    INDEX
    Explanations

    specific names

    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
    rijk
    -0.20
     abst
    -0.20
    Ļ¨
    -0.20
    HBoxLayout
    -0.20
    chestra
    -0.18
     stringBy
    -0.18
    arrière
    -0.17
     Ceremony
    -0.17
    \Bundle
    -0.17
    ulkan
    -0.17
    POSITIVE LOGITS
     nors
    0.24
    '].$
    0.20
    -Compatible
    0.20
    è¡®
    0.19
    /MIT
    0.19
    asco
    0.19
     Rihanna
    0.19
    âľ©
    0.19
     (*((
    0.19
     practition
    0.19
    Activations Density 0.008%

    No Known Activations