© 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. 20697
    Prev
    Next
    INDEX
    Explanations

    Nigerian politics and government

    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
    äºİæѤ
    -0.10
    closure
    -0.10
    ä»ĵ
    -0.10
    çªŁ
    -0.09
    æĥľ
    -0.09
    éĻĦ
    -0.09
    è·Ĺ
    -0.09
     Ñħа
    -0.09
     Exped
    -0.08
    èĭĹ
    -0.08
    POSITIVE LOGITS
    reib
    0.09
    æ±Łæ¹ĸ
    0.09
    èĨĢ
    0.08
    榷
    0.08
     Nigerian
    0.08
    éĹ¯
    0.08
    æĪļ
    0.08
    å»ĭ
    0.08
    INLINE
    0.08
    prite
    0.08
    Activations Density 0.159%

    No Known Activations