© 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. 20533
    Prev
    Next
    INDEX
    Explanations

    Afghanistan

    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
    Places
    -0.09
    åįĹæµ·
    -0.09
    æĥ¦
    -0.09
    ott
    -0.09
    .places
    -0.09
    startup
    -0.09
    讫
    -0.08
    ç¿ģ
    -0.08
    æłª
    -0.08
    仨
    -0.08
    POSITIVE LOGITS
    ä¸įçķĻ
    0.09
    lbrace
    0.09
    éĺ¿å¯Įæ±Ĺ
    0.09
    구
    0.08
    âĿ¯
    0.08
    èİ«åIJį
    0.08
     Mush
    0.08
     hamm
    0.08
    ðŁı»
    0.08
    驼
    0.08
    Activations Density 0.018%

    No Known Activations