© 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. 8873
    Prev
    Next
    INDEX
    Explanations

    Arabic and South Asian 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
    åı£æ°´
    -0.09
    ä¹ĭåĬ¿
    -0.09
    çĪ¸çĪ¸å¦Īå¦Ī
    -0.08
    åħ¨å¤©
    -0.08
    ä¸ĢäºĮ
    -0.08
    æľĢåıĹ欢è¿İ
    -0.08
    ุà¸ĩ
    -0.08
    æīĢåľ¨
    -0.08
    acs
    -0.08
    ies
    -0.07
    POSITIVE LOGITS
    izi
    0.10
     Fa
    0.10
    _FA
    0.09
    梯
    0.09
    _fa
    0.09
    磩
    0.09
    ileen
    0.09
    BILE
    0.09
     Kaw
    0.09
    ibold
    0.09
    Activations Density 0.047%

    No Known Activations