© 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. 15837
    Prev
    Next
    INDEX
    Explanations

    good, ok, fun, love

    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
    ä¸įä»ħ
    -0.20
    ä¸įä»ħä»ħæĺ¯
    -0.20
    çĴĭ
    -0.19
    ActionBar
    -0.19
    ä¸įä»ħä»ħ
    -0.19
    ITE
    -0.19
    åĪ»
    -0.19
    ä¹Łè¶ĬæĿ¥è¶Ĭ
    -0.18
    æĹ¢è¦ģ
    -0.18
    æĹ¢æĺ¯
    -0.18
    POSITIVE LOGITS
     nevertheless
    0.29
    åį´æĺ¯
    0.29
    åĢĴæĺ¯
    0.28
     nonetheless
    0.27
    æĢ»ä½ĵ
    0.26
    ä¸įéĶĻçļĦ
    0.26
    ä½Ĩæĺ¯å¦Ĥæŀľ
    0.24
    ä»įæľī
    0.24
    æ¯ķç«Łæĺ¯
    0.24
     otherwise
    0.23
    Activations Density 0.076%

    No Known Activations