© 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. 11339
    Prev
    Next
    INDEX
    Explanations

    several events

    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
    åįģä¸ĩ
    -0.20
    groupon
    -0.20
    enge
    -0.19
    æĶ¹ä¸º
    -0.19
     Ðijо
    -0.18
    游æĪıåī¯æľ¬
    -0.18
    ä¸ĥå¹´
    -0.18
    åľ°è¯´
    -0.18
    ä¸įåħģ许
    -0.18
    á´º
    -0.18
    POSITIVE LOGITS
     notable
    0.29
    æĸ°çļĦä¸Ģ
    0.28
    æľ¬åij¨
    0.25
    Several
    0.24
    åIJĦæľī
    0.23
    æĸ°è§Ħ
    0.23
     noteworthy
    0.23
    åIJĦèĩªçļĦ
    0.23
    ãģĿãĤĮãģŀãĤĮ
    0.22
     several
    0.22
    Activations Density 0.190%

    No Known Activations