© 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. 12675
    Prev
    Next
    INDEX
    Explanations

    Mr. titles and punctuation

    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
    çݯèĬĤ
    -0.22
    çķ¸
    -0.21
    ä½ĵéĩı
    -0.20
    éļ³
    -0.19
    æĹ¥æĬ¥
    -0.19
    LowerCase
    -0.19
    ç®±åŃIJ
    -0.19
    çŃĴ
    -0.19
    åı¯è¡Į
    -0.19
     hem
    -0.19
    POSITIVE LOGITS
    诣
    0.23
    çİ°ä»»
    0.23
    æ¯ķä¸ļäºİ
    0.22
    å¥¹åľ¨
    0.22
    被è¯Ħ为
    0.21
    åħ¬è®¤çļĦ
    0.21
    ä¸ļä½Ļ
    0.20
    ä¹ŁæĽ¾
    0.20
    åĩŃçĿĢ
    0.20
    æ·±åıĹ
    0.20
    Activations Density 0.386%

    No Known Activations