© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12375
    Prev
    Next
    INDEX
    Explanations

    once something happens

    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
    æģ°å¥½
    -0.21
    æŃ£æĺ¯åĽłä¸º
    -0.20
    踽
    -0.19
    æģ°æģ°
    -0.19
    ewriter
    -0.18
    æŃ£å¥½
    -0.18
    æľ¬èº«å°±æĺ¯
    -0.18
    æŶæĬ¥
    -0.18
    æľīæŶ
    -0.18
    TED
    -0.17
    POSITIVE LOGITS
    æľīäºĨ
    0.24
    没äºĨ
    0.22
    çŁ¥éģĵäºĨ
    0.22
    iver
    0.21
    åĨį说
    0.21
    ä¸ĢæŦ
    0.20
    åģļå®Į
    0.20
     дело
    0.20
    å°ĺ
    0.19
    å®ĮæĪIJåIJİ
    0.19
    Activations Density 0.068%

    No Known Activations