© 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. 50842
    Prev
    Next
    INDEX
    Explanations

    Colorado and nearby entities

    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
    epar
    -0.10
    ви
    -0.09
    Ùĥ
    -0.09
    ../../../
    -0.09
    æľŁåĨħ
    -0.09
    çĻ¸
    -0.09
    溱
    -0.09
    nger
    -0.09
    ÑĤал
    -0.09
    sWith
    -0.09
    POSITIVE LOGITS
     Springs
    0.12
     Boulder
    0.11
    Denver
    0.10
     Mesa
    0.10
    inous
    0.09
    AndWait
    0.09
    æĪijä¸įçŁ¥éģĵ
    0.09
     Rockies
    0.09
    ium
    0.09
     Denver
    0.08
    Activations Density 0.019%

    No Known Activations