© 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. 9476
    Prev
    Next
    INDEX
    Explanations

    tourism

    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
     tán
    -0.11
    æľ¬ç½ij
    -0.10
    -ahead
    -0.10
    /she
    -0.09
    ç¥Ŀç¦ı
    -0.09
    姥姥
    -0.09
    ми
    -0.09
    ings
    -0.09
    è¯ĬçĸĹ
    -0.09
    batim
    -0.09
    POSITIVE LOGITS
    è§Ĥåħī
    0.09
    unic
    0.08
    åŃ¦å®¶
    0.08
    zimmer
    0.08
    äºĭå®ľ
    0.08
    illery
    0.08
    иÑĩеÑģки
    0.08
    faction
    0.08
    ying
    0.08
    y
    0.08
    Activations Density 0.006%

    No Known Activations