© 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. 8820
    Prev
    Next
    INDEX
    Explanations

    maximum length

    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
    æİĮæı¡äºĨ
    -0.10
    大åĵ¥
    -0.09
    åĩºåİ»
    -0.09
    èģĶ
    -0.09
    nio
    -0.09
    èĽĢ
    -0.09
    åijĽ
    -0.09
    mic
    -0.08
    éĹªçĶµ
    -0.08
    å½¹
    -0.08
    POSITIVE LOGITS
    ä¸įå°ijäºİ
    0.13
    èĩ³å°ij
    0.10
    çij°
    0.09
    ä»»ä½ķå½¢å¼ı
    0.09
    ä¸įä½İäºİ
    0.09
    æ¸ħæ¥ļ
    0.09
    ombat
    0.09
    åĤ¥
    0.09
    ORIGINAL
    0.08
    åºĶèģĺ
    0.08
    Activations Density 0.032%

    No Known Activations