© 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. 8259
    Prev
    Next
    INDEX
    Explanations

    learn more about

    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
    é«ĺå°Ķ
    -0.09
    ÑĮÑİ
    -0.08
    ائÙĦ
    -0.08
    èµĦè´¨
    -0.08
    uchar
    -0.08
    çıĢ
    -0.08
    éŃĶæ³ķ
    -0.08
    æĺĶæĹ¥
    -0.08
    -margin
    -0.08
    éĽĨè£ħ
    -0.08
    POSITIVE LOGITS
    人工
    0.09
    acent
    0.09
    _drv
    0.08
    好å¤Ħ
    0.08
    .Proxy
    0.08
    åĮ¯
    0.08
    æ±ĩ
    0.08
    PRODUCT
    0.08
    iciar
    0.08
    å®ĺ
    0.08
    Activations Density 0.025%

    No Known Activations