© 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. 37520
    Prev
    Next
    INDEX
    Explanations

    steps, terraces, platforms, inclines

    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
    å¼ĵ
    -0.09
    .stroke
    -0.08
    ä¼Ļ
    -0.08
    举é£İ
    -0.08
    Ñĥг
    -0.08
    åĨħ饰
    -0.08
    å¾ħéģĩ
    -0.08
    ç«Ļéķ¿
    -0.08
    æĪIJåĪĨ
    -0.08
     Citizens
    -0.08
    POSITIVE LOGITS
    åı°éĺ¶
    0.13
    éĺ¶æ¢¯
    0.12
    éĺ¶
    0.12
    éļİ
    0.11
     cascade
    0.09
     casc
    0.09
    soc
    0.09
    åı®
    0.08
    Notifications
    0.08
    çļĦ好å¤Ħ
    0.08
    Activations Density 0.064%

    No Known Activations