© 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. 20242
    Prev
    Next
    INDEX
    Explanations

    crying related words

    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
    observe
    -0.09
     Dor
    -0.09
     dÃ¼ÅŁ
    -0.09
    oser
    -0.09
    ATORS
    -0.09
    æĬ¥å¤į
    -0.09
    滹
    -0.09
    ahoma
    -0.09
     Infragistics
    -0.08
    忤
    -0.08
    POSITIVE LOGITS
    çļĦæł·åŃIJ
    0.10
    åĵŃæ³£
    0.10
    岩
    0.10
    æĥ³å¿µ
    0.10
     Tears
    0.09
    åĨĮ
    0.09
    ä¸įæĪIJ
    0.08
     trail
    0.08
    åĥı个
    0.08
     Trail
    0.08
    Activations Density 0.026%

    No Known Activations