© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38724
    Prev
    Next
    INDEX
    Explanations

    hostile game creatures

    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
    éļIJéļIJ
    -0.10
    åįģä½³
    -0.09
    湿润
    -0.09
    ä¸Ģä¸ĸ
    -0.08
    缸éĢļ
    -0.08
    å®ī稳
    -0.08
    æļĹæļĹ
    -0.08
    éļIJ约
    -0.08
    çģ«çĥŃ
    -0.08
    èĭ£
    -0.08
    POSITIVE LOGITS
    æĿ¥è¢Ń
    0.10
    éªļæī°
    0.10
    æĮ¡ä½ı
    0.10
    å°ıå°ıçļĦ
    0.10
    åīįæĿ¥
    0.09
    åĩºçİ°åľ¨
    0.09
    ä¸Ģèµ·æĿ¥
    0.08
     вÑģÑĤÑĢеÑĩа
    0.08
    æķĮ人
    0.08
    ä¼ļè®©ä½ł
    0.08
    Activations Density 0.084%

    No Known Activations