© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19846
    Prev
    Next
    INDEX
    Explanations

    economic recovery and reopening

    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
    è¿Ļè¾ĪåŃIJ
    -0.11
    éĴ§
    -0.09
    ä¿Ŀé²ľ
    -0.09
    ued
    -0.09
    ç»Ī身
    -0.09
     Soft
    -0.09
    ä¸Ģè¾ĪåŃIJ
    -0.08
    éĹŃ
    -0.08
    AGED
    -0.08
    åĽ´
    -0.08
    POSITIVE LOGITS
    æģ¢å¤įæŃ£å¸¸
    0.24
    æģ¢å¤į
    0.23
     recovery
    0.17
    æģ¢
    0.16
    åĽŀæļĸ
    0.16
    å¤įå·¥å¤į产
    0.15
    _recovery
    0.15
     recovered
    0.15
    å¤įèĭı
    0.14
     Recovery
    0.14
    Activations Density 0.250%

    No Known Activations