© 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. 8367
    Prev
    Next
    INDEX
    Explanations

    offering explanation or help

    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
    天天
    -0.09
    è®´
    -0.09
    æįķæįī
    -0.08
    åį¯
    -0.08
    åĪĨæĺİ
    -0.08
    æįķ
    -0.08
    çŀ»
    -0.07
    梧
    -0.07
    æķĽ
    -0.07
    ä¸įä»ħä»ħæĺ¯
    -0.07
    POSITIVE LOGITS
    建议
    0.12
    åı¯ä»¥å¸®åĬ©
    0.12
    建èŃ°
    0.11
    å¸®ä½ł
    0.11
    çŃĶå¤į
    0.11
    é¢ĺ主
    0.11
    åįĶåĬ©
    0.10
    帮
    0.10
     Helping
    0.10
    å¯¹ä½ł
    0.10
    Activations Density 0.078%

    No Known Activations