© 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. 19584
    Prev
    Next
    INDEX
    Explanations

    you may

    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
     gonna
    -0.09
    ped
    -0.09
    çĽ²
    -0.08
    æĽ´è¦ģ
    -0.08
    éĤ£ä¸ĢåĪ»
    -0.08
    天ä¸ĭ
    -0.08
    å¾ĩ
    -0.08
    ugal
    -0.08
    æŃ¤åŁºç¡Ģä¸Ĭ
    -0.08
    ç»ĻäºĨ
    -0.08
    POSITIVE LOGITS
    禧
    0.10
    容è²Į
    0.09
    åłij
    0.09
    çļĦæĥħ绪
    0.08
    æľ¬äºº
    0.08
    /items
    0.08
    å°Ĩæĺ¯
    0.08
    被æįķ
    0.08
    çħ¨
    0.08
    åľ¨æĪijçļĦ
    0.08
    Activations Density 0.077%

    No Known Activations