© 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. 37121
    Prev
    Next
    INDEX
    Explanations

    made or making something

    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
    åīĤ
    -0.10
    æİīäºĨ
    -0.09
    åĿĩåĮĢ
    -0.09
    éĢīåĩº
    -0.09
    dic
    -0.08
     chop
    -0.08
     Aub
    -0.08
     Naked
    -0.08
    ä¼Ļ
    -0.08
    ä¸Ģåı¥è¯Ŀ
    -0.08
    POSITIVE LOGITS
    æī¹
    0.11
    第äºĮæī¹
    0.11
    çıŃ
    0.11
    éļĶ
    0.10
    åıĭæĥħ
    0.09
    .hxx
    0.09
    stown
    0.09
    ä¸Ńåħ³
    0.09
    åıĪä¸Ģ次
    0.09
    åĨįä¸Ģ次
    0.09
    Activations Density 0.204%

    No Known Activations