© 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. 20993
    Prev
    Next
    INDEX
    Explanations

    geography and culture

    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
    è¿Ļæĺ¯æĪij们
    -0.09
    ses
    -0.09
    ä¾
    -0.09
    è·¨è¶Ĭ
    -0.09
    heimer
    -0.09
    æºIJæ³ī
    -0.08
    她们
    -0.08
    æīįæĺ¯çľŁæŃ£
    -0.08
    annah
    -0.08
    åķĨä¼ļ
    -0.08
    POSITIVE LOGITS
    åĭī
    0.10
    Sha
    0.09
    壯
    0.08
    uppe
    0.08
    壮
    0.08
    ä¸ĢèĪ¬
    0.08
    ä¸Ģç¢Ĺ
    0.08
    ä¸įéĶĻçļĦ
    0.08
    åİĨåı²ä¸Ĭ
    0.08
    ä¸ĭéĿ¢æĪij们
    0.08
    Activations Density 0.172%

    No Known Activations