© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37190
    Prev
    Next
    INDEX
    Explanations

    more than

    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
    usan
    -0.10
    ç¼ĸåı·
    -0.09
    åĽ°éļ¾
    -0.08
    åĮĹ大
    -0.08
    æĺİæĺ¾
    -0.08
    LLU
    -0.08
    orta
    -0.08
     íĮIJ
    -0.08
    æ´º
    -0.08
    æģª
    -0.08
    POSITIVE LOGITS
    ä¸İåħ¶ä»ĸ
    0.11
     than
    0.11
    漪
    0.11
    ä»ħ次äºİ
    0.10
    æ¯Ķäºļ
    0.10
    åijĬè¯ī大家
    0.09
    说æĺ¯
    0.09
    _than
    0.09
    è¿Ħä»Ĭ为æŃ¢
    0.09
    代
    0.09
    Activations Density 0.074%

    No Known Activations