© 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. 13189
    Prev
    Next
    INDEX
    Explanations

    do/does/did + have/this/stop/stumble/think/recall

    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¦ģä¹Ī
    -0.28
    ä¸įä½Ĩ
    -0.23
    æĹ¢æĺ¯
    -0.23
    ä¸Ģæĺ¯
    -0.22
    æľ¬æĿ¥
    -0.21
    æīĢ说
    -0.21
    ä¸įå¿ħè¦ģçļĦ
    -0.21
    å®ŀåľ¨æĺ¯
    -0.20
    ç®Ģ缴
    -0.19
    æīĢåģļçļĦ
    -0.19
    POSITIVE LOGITS
    æľīä¸ĢäºĽ
    0.23
     sne
    0.22
    æľī个
    0.22
    çĤ¹åĦ¿
    0.20
    åŃĺåľ¨
    0.20
    èijĨ
    0.20
    ãģ£ãģ¨
    0.20
     however
    0.19
    æľīä¸Ģ
    0.19
    peri
    0.19
    Activations Density 0.036%

    No Known Activations