© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52876
    Prev
    Next
    INDEX
    Explanations

    asking, requesting, telling, reporting

    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
    æĮĤ
    -0.09
    æİ¥åĪ°
    -0.09
    æİĽ
    -0.09
    æĮĤåľ¨
    -0.09
    æĸ¼æĺ¯
    -0.08
    éĢĤçĶ¨äºİ
    -0.08
    麥
    -0.08
     ÑģÑĥÑīеÑģÑĤв
    -0.08
    OLDER
    -0.08
    write
    -0.08
    POSITIVE LOGITS
    æ±Ĥ
    0.09
    ë´ĩ
    0.09
    apper
    0.09
    请éĢīæĭ©
    0.09
    æīĵæŀ¶
    0.09
    æľ¬æĬ¥
    0.09
    åķĨéĩı
    0.09
     approves
    0.09
    æĮij
    0.09
    iba
    0.09
    Activations Density 0.050%

    No Known Activations