© 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. 5465
    Prev
    Next
    INDEX
    Explanations

    as...than comparative phrases

    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
    æľīç§į
    -0.10
     haze
    -0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    KeyType
    -0.09
    å°±æĺ¯è¿Ļæł·
    -0.08
     Ballard
    -0.08
    ä¸į认è¯Ĩ
    -0.08
    æ¯Ķäºļ
    -0.08
    éľĦ
    -0.08
    ä¸įåıªæĺ¯
    -0.08
    POSITIVE LOGITS
    éĤ£äºĽ
    0.11
    åįķ纯çļĦ
    0.10
    åįķ纯
    0.10
    çĽ¸ä¼´
    0.10
    好好
    0.10
    éĿĻéĿĻ
    0.09
    平淡
    0.09
    åģļ个
    0.09
    ä»»ä½ķ
    0.09
    æľ¬èº«çļĦ
    0.09
    Activations Density 0.053%

    No Known Activations