© 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. 9048
    Prev
    Next
    INDEX
    Explanations

    Spain and its cities/regions

    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
    夷
    -0.10
    apo
    -0.10
    åIJĪçIJĨ
    -0.10
    æīĵä»Ĺ
    -0.09
    çļĩä¸Ĭ
    -0.09
    æĤ¯
    -0.09
    çĪ·
    -0.09
    ops
    -0.08
    çİ·
    -0.08
    ez
    -0.08
    POSITIVE LOGITS
    åīij
    0.09
    çłģ
    0.09
    çĵ¦
    0.09
    ooter
    0.09
    è¦ģçľĭ
    0.09
     Alonso
    0.09
    Spain
    0.09
    _FL
    0.09
    anja
    0.08
     hoe
    0.08
    Activations Density 0.050%

    No Known Activations