© 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. 10852
    Prev
    Next
    INDEX
    Explanations

    music practice rooms

    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
    æľĢå¿«çļĦ
    -0.22
    ä¿ĺ
    -0.22
    æľī趣çļĦ
    -0.21
    åģıåIJij
    -0.21
    趣
    -0.21
    å¢Ĵ
    -0.21
    ç½¹
    -0.21
    ç³Ĭ
    -0.20
    ä¸īåĪĨ
    -0.19
     losing
    -0.19
    POSITIVE LOGITS
    åĩĮ
    0.24
     disruptive
    0.24
    åįłçĶ¨
    0.23
    ä¸Ģå¾ĭ
    0.22
    人人
    0.21
    å¹²æī°
    0.21
    æī°ä¹±
    0.20
    åĩºåħ¥
    0.20
    å½±åĵį
    0.19
     DIST
    0.19
    Activations Density 0.092%

    No Known Activations