© 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. 8211
    Prev
    Next
    INDEX
    Explanations

    Alain, Bob, Bloomberg, Action

    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
    olumn
    -0.09
    åĨ²éĶĭ
    -0.09
    æŁľ
    -0.08
    èģĮ称
    -0.08
    æĺ¯æľī
    -0.08
    oplay
    -0.08
    à¸Ńาย
    -0.08
     возÑĢаÑģÑĤ
    -0.08
    itori
    -0.08
    iting
    -0.08
    POSITIVE LOGITS
    çļĦçħ§çīĩ
    0.12
    æijĦ
    0.11
    ä¼ģä¸ļæıIJä¾Ľ
    0.10
    示æĦı
    0.10
    ä¾ĽåĽ¾
    0.10
    çīĪæĿĥå½ĴåİŁ
    0.09
    è°ħ解
    0.09
    æĶ¾å¤§
    0.09
    çīĪæĿĥå½Ĵ
    0.09
    æįķæįī
    0.09
    Activations Density 0.104%

    No Known Activations