© 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. 20336
    Prev
    Next
    INDEX
    Explanations

    verb + it

    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
    æĦı大
    -0.09
    cks
    -0.09
    afil
    -0.08
    rets
    -0.08
    ritt
    -0.08
    第ä¸Ģ次
    -0.08
    ä¸Ģç³»åĪĹ
    -0.08
     ÑħозÑıйÑģÑĤв
    -0.08
    æľ¬ç«Ļ
    -0.08
    顽
    -0.07
    POSITIVE LOGITS
    å®ĥ
    0.34
    å®ĥæĺ¯
    0.29
    å®ĥ们
    0.29
    æĬĬå®ĥ
    0.28
     it
    0.26
     them
    0.25
    使ä¹ĭ
    0.25
    å®ĥåı¯ä»¥
    0.24
    ãģĿãĤĮãĤĴ
    0.24
    å°Ĩåħ¶
    0.23
    Activations Density 0.521%

    No Known Activations