© 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. 8621
    Prev
    Next
    INDEX
    Explanations

    panic and alarm

    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
    åĢĶ
    -0.10
    åĶ¾
    -0.09
    çijķ
    -0.09
    otte
    -0.09
    ä»»æĢ§
    -0.09
    æ±Łå±±
    -0.09
    urette
    -0.09
    ç»Ĭ
    -0.09
    èģĶåIJĪä¼ļ
    -0.09
    _ETH
    -0.09
    POSITIVE LOGITS
    æģIJæħĮ
    0.22
     panic
    0.19
    æħĮ
    0.19
     panicked
    0.16
    çĿĢæĢ¥
    0.15
    çĦ¦æĢ¥
    0.15
     Panic
    0.15
    æĥ¶
    0.15
    panic
    0.14
    çĦ¦èĻij
    0.14
    Activations Density 0.058%

    No Known Activations