© 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. 13411
    Prev
    Next
    INDEX
    Explanations

    Americans and Australians

    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
    åħ¨çIJĥ
    -0.22
    å°Ħ
    -0.21
     Worldwide
    -0.21
    éĵº
    -0.20
    è·¨
    -0.20
     worldwide
    -0.19
    õ
    -0.19
    ær
    -0.19
    cq
    -0.19
    åħ¨çIJĥæľĢ大
    -0.19
    POSITIVE LOGITS
    æ¿Ĥ
    0.24
    æľ¬åľŁ
    0.22
    éķĸ
    0.22
    ä¸įåIJĥ
    0.21
    以åıĬåħ¶ä»ĸ
    0.20
    çŃīåľ°
    0.20
    å°¼åħĭ
    0.19
    æĪĸåħ¶ä»ĸ
    0.19
    éŃĶæ³ķå¸Ī
    0.18
     Steph
    0.18
    Activations Density 0.993%

    No Known Activations