© 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. 14070
    Prev
    Next
    INDEX
    Explanations

    questions and specific terms

    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
     Homes
    -0.22
    åħ¥æĪ·
    -0.20
    åѤç«ĭ
    -0.19
    çŃĨ
    -0.19
    åħļæł¡
    -0.19
    æıĨ
    -0.19
    çķĪ
    -0.19
    å¤Ħå¤Ħ
    -0.19
    éĵĻ
    -0.18
     indirect
    -0.18
    POSITIVE LOGITS
    éĢĥçĶŁ
    0.39
    çĸıæķ£
    0.34
    楼梯
    0.28
    æĭ¥æĮ¤
    0.27
    伤亡
    0.25
    çĶŁæŃ»
    0.23
    æľīåºı
    0.23
     Beste
    0.22
    _SF
    0.22
    åľºéĿ¢
    0.22
    Activations Density 0.028%

    No Known Activations