© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8660
    Prev
    Next
    INDEX
    Explanations

    difficulty, challenging, hard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    æĽ´å¥½çļĦ
    -0.10
    è¿ĻæĶ¯
    -0.09
    æĪ¿ä¸ľ
    -0.09
    æĽ´å¥½
    -0.09
    anka
    -0.09
    æĢ¥äºİ
    -0.09
    æľ¬éĴ±
    -0.09
    æĽ´å¥½åľ°
    -0.09
    ensively
    -0.09
    飽
    -0.09
    POSITIVE LOGITS
    éļ¾åº¦
    0.19
    åĽ°éļ¾
    0.16
    æĮijæĪĺ
    0.16
    åĽ°éĽ£
    0.14
     difficulty
    0.13
    èī°éļ¾
    0.13
    èĢĥéªĮ
    0.12
    difficulty
    0.12
    ä»»åĬ¡
    0.12
     challenging
    0.11
    Activations Density 0.073%

    No Known Activations