© 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. 4907
    Prev
    Next
    INDEX
    Explanations

    Spain, Spanish people and places

    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
     Cly
    -0.09
    éĤĻ
    -0.09
    aukee
    -0.09
    å¤ļåįĬ
    -0.08
    ä½ĵåŀĭ
    -0.08
    æ¿®
    -0.08
    岫
    -0.08
    Mul
    -0.08
    ospace
    -0.08
    icolor
    -0.08
    POSITIVE LOGITS
    Spain
    0.13
    西çıŃçīĻ
    0.13
     Spain
    0.12
    æ¹ĸåįĹçľģ
    0.11
     Spanish
    0.11
    西çĶ²
    0.10
    æ¹ĸåįĹ
    0.10
    iest
    0.10
     Zap
    0.10
    å·´æĸ¯
    0.09
    Activations Density 0.097%

    No Known Activations