© 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
    2. Qwen2.5-7B-IT
    3. 20-MATRYOSHKA-65K
    4. 3614
    Prev
    Next
    INDEX
    Explanations

    access

    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
    UMMY
    -0.20
     semiclass
    -0.19
    sten
    -0.19
    __).
    -0.19
    assertTrue
    -0.18
    Ø®ÙĬÙĦ
    -0.18
    uxtap
    -0.18
    bach
    -0.18
    loff
    -0.18
    liness
    -0.18
    POSITIVE LOGITS
     access
    0.28
    ç»Ī身
    0.26
    享æľī
    0.24
    享ç͍
    0.24
    -widgets
    0.24
    ç»ĪçĶŁ
    0.23
     Garr
    0.23
    享
    0.23
     lifetime
    0.22
     professionally
    0.22
    Activations Density 0.512%

    No Known Activations