© 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. 12201
    Prev
    Next
    INDEX
    Explanations

    final or last duration

    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
    ä¸ĭ次
    -0.23
     next
    -0.19
    第ä¸ĢæŶéĹ´
    -0.19
    éĩijå¥ĸ
    -0.19
    çľ¨çľ¼
    -0.19
    ãģĽãģĦ
    -0.18
    主è¦ģåİŁåĽł
    -0.18
    æŃ£å®Ĺ
    -0.18
    æĹ©å°±
    -0.18
    .cum
    -0.18
    POSITIVE LOGITS
    åĨ²åĪº
    0.23
    å°¤åħ¶æĺ¯
    0.22
    å°¤åħ¶
    0.22
    å¼Ģå§ĭ
    0.22
    åĨ³æĪĺ
    0.20
     Singleton
    0.20
    åºıå¹ķ
    0.19
    éĥ¨åĪĨ
    0.18
    ocrin
    0.18
    åŃļ
    0.18
    Activations Density 0.038%

    No Known Activations