© 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. 14705
    Prev
    Next
    INDEX
    Explanations

    induction and electromagnetic radiation

    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
    å½¹
    -0.19
    人大
    -0.19
    Processing
    -0.19
    åĬłå·¥
    -0.18
    REN
    -0.18
     dead
    -0.18
    å¯Ĥ
    -0.18
    æī
    -0.18
    iat
    -0.17
    åĵģ
    -0.17
    POSITIVE LOGITS
    çľĭä¸įè§ģ
    0.22
    uzzi
    0.21
     Diane
    0.19
    iÅŁ
    0.18
    åģľè½¦
    0.18
    _stamp
    0.18
    :image
    0.17
    isting
    0.17
    èıĮ
    0.17
    åĿļæĮģä¸įæĩĪ
    0.17
    Activations Density 0.002%

    No Known Activations