© 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. 22327
    Prev
    Next
    INDEX
    Explanations

    empower / empowering

    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
    æĪ¿åŃIJ
    -0.10
    ä¸¥æł¼èIJ½å®ŀ
    -0.09
    çłĶåıijæĬķåħ¥
    -0.09
    èĶ¼
    -0.09
    ì´ī
    -0.09
    tracer
    -0.08
    çĤĻ
    -0.08
    çīĮåŃIJ
    -0.08
    ÑĪие
    -0.08
    pite
    -0.08
    POSITIVE LOGITS
    /disable
    0.11
    ä¸ĢæĬĬ
    0.09
    OMB
    0.08
    æ¶ŀ
    0.08
    主æĿĥ
    0.08
    æī¹è¯Ħ
    0.08
    æĪĺæĸĹåĬĽ
    0.08
    çĹ´
    0.08
    hel
    0.08
    hed
    0.08
    Activations Density 0.013%

    No Known Activations