© 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. 5286
    Prev
    Next
    INDEX
    Explanations

    Americans, redneck, Trump, Arizona

    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
    åľ¨åºĬä¸Ĭ
    -0.11
    èººåľ¨åºĬä¸Ĭ
    -0.09
    éĺ³åı°
    -0.09
    asaki
    -0.08
    è¹Ĵ
    -0.08
     barcelona
    -0.08
    æŀ¶
    -0.08
    沤
    -0.08
    .Singleton
    -0.08
    ť
    -0.08
    POSITIVE LOGITS
    çŃĭ
    0.10
    æĦŁåıĹ
    0.10
     Midwest
    0.10
    乡éķĩ
    0.09
    åĨľæ°ij
    0.09
    zin
    0.09
    åĨľæĿij
    0.09
    å¼łè´´
    0.09
    æĭĽæĶ¶
    0.09
    æĤ´
    0.08
    Activations Density 0.164%

    No Known Activations