© 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. 13194
    Prev
    Next
    INDEX
    Explanations

    '>', '>', 'next', 'previous'

    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
    鸳
    -0.21
    åĪ©çĽĬ
    -0.20
    以为
    -0.18
    æľŁ
    -0.18
    è°¨
    -0.17
    VICE
    -0.17
    endon
    -0.17
     Julien
    -0.17
    finder
    -0.17
    endcode
    -0.17
    POSITIVE LOGITS
    漫æŃ¥
    0.21
    置身
    0.20
    æĤłæĤł
    0.19
    满满
    0.19
    缬
    0.18
    主é¢ĺæķĻèĤ²
    0.18
    å°±è¿Ļä¹Ī
    0.17
     gez
    0.17
     lap
    0.17
    isle
    0.17
    Activations Density 0.003%

    No Known Activations