© 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. 9033
    Prev
    Next
    INDEX
    Explanations

    just because

    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
    uth
    -0.09
    ä¸įå¾Ĺä¸į
    -0.09
    åĩĿ
    -0.08
    çIJĨæĥ³çļĦ
    -0.08
     leaving
    -0.08
    æįŁ
    -0.08
    ÑĤол
    -0.08
    оп
    -0.08
    å¿ħé¡»
    -0.08
    åĢ¦
    -0.08
    POSITIVE LOGITS
    è¹ĩ
    0.11
    æݬ
    0.10
    è´¸
    0.10
    绶
    0.10
    äºİæѤ
    0.10
    åĻİ
    0.10
    侥幸
    0.10
    åĩłä¸ªäºº
    0.10
    åħ¥éĢī
    0.10
    髹
    0.09
    Activations Density 0.039%

    No Known Activations