© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13079
    Prev
    Next
    INDEX
    Explanations

    luc, lucas, lucy, lucien, lucille, lucchese

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    auce
    -0.18
    untas
    -0.17
    gie
    -0.17
    даеÑĤÑģÑı
    -0.17
    лон
    -0.16
    è¾İ
    -0.16
    çĸ¤
    -0.16
    yh
    -0.15
    uated
    -0.15
    ãĤ¿ãĥ«
    -0.15
    POSITIVE LOGITS
    itch
    0.20
    ly
    0.16
    ous
    0.16
    è¿Ļ个æŶåĢĻ
    0.15
    -eyed
    0.15
    angelo
    0.15
    ously
    0.15
    rig
    0.14
    affle
    0.14
    rate
    0.14
    Activations Density 0.024%

    No Known Activations