© 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. 51740
    Prev
    Next
    INDEX
    Explanations

    independent national electoral commission

    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
    åIJĦ个æĸ¹éĿ¢
    -0.09
    åĬ«
    -0.09
    0
    -0.09
    åIJ¯èĴĻ
    -0.09
    tractive
    -0.09
    å°ıæľĭåıĭ
    -0.08
    6
    -0.08
    åĪĨæѧ
    -0.08
    ä¸Ģ页
    -0.08
    ä¹Łåıªèĥ½
    -0.08
    POSITIVE LOGITS
    oba
    0.10
    è¿Ļæł·çļĦè¯Ŀ
    0.09
    横
    0.09
    lish
    0.09
    çģ¾å®³
    0.09
     Ballard
    0.09
     обÑĬ
    0.09
    æľīæŶ
    0.09
    idth
    0.08
    ité
    0.08
    Activations Density 0.009%

    No Known Activations