© 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. 37418
    Prev
    Next
    INDEX
    Explanations

    New York place names

    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
    ูà¹Ī
    -0.10
    æĸ«
    -0.09
     Saudi
    -0.09
    oday
    -0.08
     Saudis
    -0.08
    éĿĴå²Ľå¸Ĥ
    -0.08
    diamond
    -0.08
    æŃī
    -0.08
    æ²Ļçī¹
    -0.08
    å®ķ
    -0.08
    POSITIVE LOGITS
    æ¨Ł
    0.09
    æĿĪ
    0.09
    çĵ·
    0.09
    ĥĿ
    0.08
    京津åĨĢ
    0.08
    ä¼ļåIJĮ
    0.08
    èĹ¿
    0.08
    èµĤ
    0.08
    oti
    0.08
    _extent
    0.08
    Activations Density 0.233%

    No Known Activations