© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22619
    Prev
    Next
    INDEX
    Explanations

    various comparatives and superlatives

    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
    ä¸įåIJĮäºİ
    -0.11
    uled
    -0.09
    æ¯Ķäºļ
    -0.09
    ahead
    -0.09
    åľ°ä¸Ń
    -0.09
    ä»ĸ们æĺ¯
    -0.08
    erver
    -0.08
    ä¼ļéķ¿
    -0.08
    çĸ¾çĹħçļĦ
    -0.08
    åħĥ
    -0.08
    POSITIVE LOGITS
    å¹³åĿĩæ°´å¹³
    0.14
    ä»»ä½ķæŶåĢĻ
    0.12
    æľīä»»ä½ķ
    0.11
    åįķ纯çļĦ
    0.11
    ä»»ä½ķä¸Ģ个
    0.11
    mere
    0.11
    å¹³åĿĩ
    0.10
    æľ¬èº«
    0.10
    æīĢèĥ½
    0.10
    ä½ķåĨµ
    0.09
    Activations Density 0.091%

    No Known Activations