© 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. 9422
    Prev
    Next
    INDEX
    Explanations

    past tense verbs describing states

    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
    家ä½ı
    -0.12
    оÑı
    -0.09
    åĴĮå®ĮåĸĦ
    -0.09
    å¨ĵ
    -0.09
    ivic
    -0.09
    ãģ©
    -0.08
    身ä½ĵåģ¥åº·
    -0.08
     sacrific
    -0.08
    éĥ¡
    -0.08
    天çĶŁ
    -0.08
    POSITIVE LOGITS
    æĪIJ为ä¸Ģ个
    0.12
    éĩĮçļĦ
    0.12
    沦
    0.11
    åĨħçļĦ
    0.11
    åħħæĸ¥
    0.11
    è£ħä¿®
    0.10
    主人
    0.10
    mates
    0.10
    éĹŃ
    0.10
    åıĺæĪIJäºĨ
    0.10
    Activations Density 0.229%

    No Known Activations