© 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. 36802
    Prev
    Next
    INDEX
    Explanations

    American and related adjectives

    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
    edin
    -0.11
    å¨ĺå¨ĺ
    -0.09
    onic
    -0.09
    lam
    -0.09
    BIND
    -0.09
    erah
    -0.09
    ä¸ĸçķĮä¸Ģæµģ
    -0.09
    /she
    -0.09
     noqa
    -0.09
    oga
    -0.09
    POSITIVE LOGITS
     Samoa
    0.13
    佬
    0.12
    åĬłå·ŀ
    0.10
    ized
    0.10
    å¤ļåľ°
    0.10
    纽约
    0.09
    éĥĬåĮº
    0.09
    ifest
    0.09
     Latina
    0.09
     اÙĦØ´ÙħاÙĦ
    0.09
    Activations Density 0.051%

    No Known Activations