© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15367
    Prev
    Next
    INDEX
    Explanations

    percent or half of

    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
    éĿ¢ç§¯çº¦
    -0.23
    é¼IJ
    -0.23
    ä»»ä½ķ人éĥ½
    -0.21
    åĽłä¸ºæĪij们
    -0.20
    æĪĸåħ¶ä»ĸ
    -0.20
    çľĭå¾Ĺ
    -0.20
    ä¸įæĸŃåĪĽæĸ°
    -0.19
    åIJĽ
    -0.19
    åĽłä¸ºå¥¹
    -0.19
    åĪ°æĿ¥
    -0.19
    POSITIVE LOGITS
    æİ¥åıĹäºĨ
    0.20
    éĹ®åį·
    0.20
    anzi
    0.20
    ackers
    0.19
     scare
    0.19
    iley
    0.18
    å°Ĩèĩªå·±çļĦ
    0.18
    æ±Ģ
    0.18
     jack
    0.18
    å¼±
    0.17
    Activations Density 0.051%

    No Known Activations