© 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. 15136
    Prev
    Next
    INDEX
    Explanations

    spray-drying and stabilization

    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
    è¦ģåģļåĪ°
    -0.20
    ä¸ĢåIJ¬
    -0.20
    æīĵå¼ĢäºĨ
    -0.19
    .enum
    -0.18
    çĻ¾å¼º
    -0.18
    èĤī
    -0.18
    è¾ĥ强çļĦ
    -0.18
    å¼ĢæĶ¯
    -0.18
    -strong
    -0.18
     domina
    -0.18
    POSITIVE LOGITS
    utely
    0.23
    庶
    0.21
    pora
    0.21
    åĿĬ
    0.20
    河边
    0.20
    夤
    0.20
    ør
    0.19
    èµ°åĩºæĿ¥
    0.19
     stage
    0.19
    ihar
    0.19
    Activations Density 0.008%

    No Known Activations