© 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. 12897
    Prev
    Next
    INDEX
    Explanations

    Rome and Roman Catholic

    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
    æĮŀ
    -0.17
    gle
    -0.16
    ÃŃv
    -0.16
    iali
    -0.16
    oes
    -0.15
    edly
    -0.15
    reso
    -0.15
    noon
    -0.15
    ounder
    -0.15
    ëªħ
    -0.15
    POSITIVE LOGITS
    å°¼äºļ
    0.27
    efeller
    0.20
    Ñģл
    0.19
    ically
    0.16
    ical
    0.16
    ographic
    0.16
    аÑĪ
    0.16
    ita
    0.16
     trá»Ŀi
    0.15
    ear
    0.15
    Activations Density 0.015%

    No Known Activations