© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20840
    Prev
    Next
    INDEX
    Explanations

    leadership roles

    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
    çĥ¹
    -0.10
    æ¶īå«Į
    -0.10
    ç¬ij声
    -0.09
    å¾ĺå¾Ĭ
    -0.09
    åIJĮäºĭ们
    -0.09
    ulen
    -0.09
    æ¼Ĥ
    -0.09
    å;
    -0.09
    æºĺ
    -0.08
    éĩİ
    -0.08
    POSITIVE LOGITS
    带åĬ¨
    0.11
    ä¼
    0.10
    å®£ä¼łæ´»åĬ¨
    0.10
    åħĪéĶĭ
    0.10
    鬼
    0.10
    å¼ķé¢Ĩ
    0.09
    èĪĤ
    0.09
    ONT
    0.09
    äºĴ缸
    0.09
    大ä¼ļ
    0.09
    Activations Density 0.060%

    No Known Activations