© 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. 20626
    Prev
    Next
    INDEX
    Explanations

    music elements

    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
    æľĢå¿«
    -0.10
    ucer
    -0.10
    å°ıé¾Ļ
    -0.10
    åĬĽè¿ĺæĺ¯
    -0.10
    积
    -0.10
    积累
    -0.10
    åī©ä¸ĭ
    -0.09
    ÌĢ
    -0.09
     Thần
    -0.09
    æı¡
    -0.09
    POSITIVE LOGITS
    åĪĩåħ¥
    0.09
    åIJ¬èµ·æĿ¥
    0.09
    ä½ľçĶ¨
    0.08
     presence
    0.08
     except
    0.07
    丹
    0.07
    ç®IJ
    0.07
    æ¯ıæ¯ı
    0.07
    çī¹èī²
    0.07
    ddf
    0.07
    Activations Density 0.032%

    No Known Activations