© 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. 15287
    Prev
    Next
    INDEX
    Explanations

    circumventing problems

    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
    ä¹°åĪ°
    -0.25
    ä¸ĩä¸Ģ
    -0.22
    ä¸ĩåįĥ
    -0.20
    çļĦ人æĿ¥è¯´
    -0.18
    åĶ®
    -0.18
    æľīå¾Īå¤ļç§į
    -0.18
    ä¹°äºĨ
    -0.17
     corpor
    -0.17
    Compiled
    -0.17
    çĶŁäº§åĬĽ
    -0.17
    POSITIVE LOGITS
    缸åºĶ
    0.30
    缸åºĶçļĦ
    0.29
    ä»į
    0.28
    ä»įçĦ¶
    0.27
     accordingly
    0.27
    é¢Ŀå¤ĸ
    0.26
    ä»įæĺ¯
    0.25
    ä¾ĿçĦ¶
    0.24
    äºĪ以
    0.23
    ä»įæľī
    0.23
    Activations Density 0.083%

    No Known Activations