© 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. 12132
    Prev
    Next
    INDEX
    Explanations

    Hope this helps

    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
    èµ
    -0.19
    uchar
    -0.19
    æīĢä»¥åľ¨
    -0.19
    è§ij
    -0.19
    æķ´ä¸ª
    -0.18
    尾巴
    -0.18
    óm
    -0.18
    å¬ĸ
    -0.17
    wizard
    -0.17
    æĹºçĽĽ
    -0.17
    POSITIVE LOGITS
    æľīæīĢ帮åĬ©
    0.27
     helpful
    0.27
     Helpful
    0.23
    为æĤ¨æıIJä¾Ľ
    0.23
     useful
    0.22
    ÑģÑĤÑĥп
    0.21
    ä¿¡æģ¯æľįåĬ¡
    0.21
    帮åĬ©
    0.21
    å¯¹ä½ł
    0.21
    解çŃĶ
    0.21
    Activations Density 0.048%

    No Known Activations