© 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. 8564
    Prev
    Next
    INDEX
    Explanations

    batch processing or conversion

    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
    éĺģ
    -0.11
    æī§
    -0.09
    诤
    -0.08
     Kelvin
    -0.08
    _bullet
    -0.08
    çĮ±
    -0.08
    æį¢ä¸ª
    -0.08
     Scrap
    -0.08
    BSD
    -0.08
    ëĤľ
    -0.08
    POSITIVE LOGITS
    æī¹
    0.17
    æī¹éĩı
    0.16
     batch
    0.16
     processing
    0.15
    大æī¹
    0.15
    å¤ĦçIJĨ
    0.15
    .batch
    0.14
    åĬłå·¥
    0.14
     batches
    0.14
    batch
    0.14
    Activations Density 0.153%

    No Known Activations