© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9593
    Prev
    Next
    INDEX
    Explanations

    California locations

    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
    éĤ¢åı°
    -0.14
    éĺľéĺ³
    -0.12
    å¾IJå·ŀ
    -0.11
    å¼Ģå°ģ
    -0.11
    æ²³åĮĹ
    -0.11
    京津åĨĢ
    -0.10
    æ²³åįĹçľģ
    -0.10
    åįİåĮĹ
    -0.10
    çķ¿
    -0.10
    æ±´
    -0.09
    POSITIVE LOGITS
    åĬłå·ŀ
    0.15
     california
    0.13
     California
    0.13
    æĪIJéĥ½å¸Ĥ
    0.13
    æĿŃå·ŀå¸Ĥ
    0.13
    California
    0.12
     San
    0.12
     Californ
    0.12
     Calif
    0.12
    Pacific
    0.12
    Activations Density 0.243%

    No Known Activations