© 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. 15202
    Prev
    Next
    INDEX
    Explanations

    in the face of or in the wake 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
    人次
    -0.20
    ä¸Ģ缴åĪ°
    -0.19
    çļĦç§ĺå¯Ĩ
    -0.19
    å½ĵä¹ĭæĹłæĦ§
    -0.18
    éķ¿æ±Ł
    -0.18
    å±ĤéĿ¢
    -0.18
    éĩIJ
    -0.18
    ä½ıåľ¨
    -0.18
    çķĻåľ¨
    -0.18
    们çļĦ
    -0.17
    POSITIVE LOGITS
    åĪ°æĿ¥
    0.21
     adversity
    0.21
    æĿ¡ä»¶ä¸ĭ
    0.20
    诱æĥij
    0.20
    åį³å°ĨåĪ°æĿ¥
    0.19
    èĭ¦èĭ¦
    0.19
    .fig
    0.19
    /out
    0.19
    è¿«ä¸įåıĬ
    0.19
    大éĩı
    0.19
    Activations Density 0.046%

    No Known Activations