© 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. 4474
    Prev
    Next
    INDEX
    Explanations

    geographic locations in the United States

    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
    æĦı
    -0.10
     Cel
    -0.09
    Cel
    -0.09
    ä¼¼
    -0.09
     CEL
    -0.09
    æ¶Ī
    -0.09
    adar
    -0.09
    edar
    -0.08
     cel
    -0.08
     دائÙħ
    -0.08
    POSITIVE LOGITS
    åIJĦçľģ
    0.12
    åĮĹæĸ¹
    0.10
    åIJĦåľ°
    0.10
    åľ¨åħ¨åĽ½
    0.10
    å¤ļåľ°
    0.09
    åħ¨åĽ½
    0.09
     Abram
    0.09
    åı¯ä¿¡
    0.09
     Aad
    0.09
    Alabama
    0.09
    Activations Density 0.066%

    No Known Activations