© 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. 52297
    Prev
    Next
    INDEX
    Explanations

    again after hours today reversed increases

    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
    说åĪ°è¿ĻéĩĮ
    -0.10
    æľīåĬ©äºİ
    -0.10
    جا
    -0.09
    taÅŁ
    -0.09
    ä¸įåıªæĺ¯
    -0.09
    æľīçĽĬ
    -0.09
    çĽ¼æľĽ
    -0.09
    æĶ¾è¿ĩ
    -0.09
    çĭ¬è§Ĵ
    -0.09
    éĻ¢åŃIJ
    -0.09
    POSITIVE LOGITS
    è¿ĺæĺ¯ä¼ļ
    0.13
    åĨį次
    0.12
    åĨį度
    0.12
    ä»įæŧ
    0.12
    è¿ĺæĺ¯è¦ģ
    0.12
     again
    0.12
    éĩįæĸ°
    0.11
     reint
    0.11
     Again
    0.10
     ëĭ¤ìĭľ
    0.10
    Activations Density 0.142%

    No Known Activations