© 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. 7624
    Prev
    Next
    INDEX
    Explanations

    sell-off, selloff, rises, supply, strength

    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
    åĽłåľ°åĪ¶å®ľ
    -0.09
    æĶ¹åĪ¶
    -0.09
    èİĺ
    -0.09
    haps
    -0.09
     невоз
    -0.08
    é£ŀ
    -0.08
    èģĬ
    -0.08
    cie
    -0.08
    åĮ¡
    -0.08
    éĥ¢
    -0.08
    POSITIVE LOGITS
    æģIJæĥ§
    0.11
    æĭħ忧
    0.10
    æģIJæħĮ
    0.10
    忧èĻij
    0.10
    éĩijä»·
    0.10
    ARB
    0.09
    	panic
    0.09
    åĸĩåıŃ
    0.09
    æĥħ绪
    0.09
    umo
    0.09
    Activations Density 0.240%

    No Known Activations