© 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. 6708
    Prev
    Next
    INDEX
    Explanations

    if ... you

    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
    为äºĨ让
    -0.11
    enet
    -0.09
    igm
    -0.08
    缸æ¯Ķäºİ
    -0.08
    çľĭå¾ħ
    -0.08
    abe
    -0.08
     whenever
    -0.08
    ÑĮе
    -0.08
    åĢļ
    -0.08
    åºIJ
    -0.08
    POSITIVE LOGITS
    ãģĿãĤĮãģĮ
    0.10
    æĺ¯ä¸Ģ件
    0.10
    è¿Ļæł·åģļ
    0.10
    жа
    0.09
    åIJ¦åĪĻ
    0.09
    å®ĥ们
    0.09
    æ¦ķ
    0.09
    åĨĴçĿĢ
    0.09
    ä¸ĢåĪĩéĥ½
    0.09
    ä»ĸ们
    0.09
    Activations Density 0.081%

    No Known Activations