© 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. 13020
    Prev
    Next
    INDEX
    Explanations

    i5, HD, A9, PPro

    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
    Bas
    -0.19
    è°®
    -0.19
    antic
    -0.18
    èĥ¡åŃIJ
    -0.18
    atory
    -0.18
    icine
    -0.18
    ation
    -0.18
    ican
    -0.18
     Interstate
    -0.17
     Bas
    -0.17
    POSITIVE LOGITS
     ден
    0.19
    ä¿Ŀä¿®
    0.19
    寡
    0.18
    çİĭæľĿ
    0.18
     SOUND
    0.18
    ohn
    0.18
     UNKNOWN
    0.17
    ëıĮ
    0.17
    .Clock
    0.17
    家éĩĮ
    0.17
    Activations Density 0.006%

    No Known Activations