© 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. 13982
    Prev
    Next
    INDEX
    Explanations

    United States Court of Appeals

    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
    ppe
    -0.22
    ulos
    -0.21
    æľĽ
    -0.19
    ä»ķ
    -0.19
    urat
    -0.19
    loc
    -0.18
    á»ģn
    -0.18
    zoom
    -0.18
    prot
    -0.18
    éĢģä¸Ĭ
    -0.17
    POSITIVE LOGITS
    åIJĸ
    0.19
    èī¯å¥½çļĦ
    0.19
    é©Ĺ
    0.19
    ReadOnly
    0.18
    è¦Ĩ
    0.18
    太é«ĺ
    0.18
    çļĦèī¯å¥½
    0.18
    æłĢ
    0.17
    éĿŀ常好çļĦ
    0.17
    åıijæĶ¹
    0.17
    Activations Density 0.008%

    No Known Activations