© 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. 37341
    Prev
    Next
    INDEX
    Explanations

    concessions and contrasts

    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
    éĤ£äºĽ
    -0.09
    å°ıä¼Ļä¼´
    -0.09
    è·¯è¿ĩ
    -0.08
    holm
    -0.08
    å°±æĦıåij³çĿĢ
    -0.08
    åĬŀäºĭå¤Ħ
    -0.08
    èį¯ä¸ļ
    -0.08
    å½Ĺ
    -0.08
    è·¯çģ¯
    -0.08
    chu
    -0.08
    POSITIVE LOGITS
    åĿļ
    0.09
     not
    0.09
    sus
    0.09
    åĿļåĨ³
    0.09
    åĢļ
    0.08
    .jquery
    0.08
    è¿ĺä¸įæĺ¯
    0.08
    PTH
    0.08
    ä¸įåĨįæĺ¯
    0.08
    å¼Ģåı£
    0.08
    Activations Density 0.021%

    No Known Activations