© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 26473
    Prev
    Next
    INDEX
    Explanations

    focus on

    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
    å±IJ
    -0.09
    æīįæĺ¯
    -0.09
    /slick
    -0.09
     sexes
    -0.09
    æīįæĺ¯çľŁæŃ£
    -0.09
    åĪ°æľŁ
    -0.09
    綦
    -0.09
    ÙĬات
    -0.09
    çļĦçĶŁåij½
    -0.09
    ocos
    -0.09
    POSITIVE LOGITS
    è¿Ļä¸ĢçĤ¹
    0.13
     how
    0.12
    æŁIJä¸Ģ
    0.12
    大å±Ģ
    0.12
     whether
    0.11
    çļĦæĺ¯
    0.11
    éĤ£äºĽ
    0.10
    ä»Ģä¹Īåij¢
    0.10
    è¿ĻçĤ¹
    0.10
     areas
    0.10
    Activations Density 0.036%

    No Known Activations