© 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. 20397
    Prev
    Next
    INDEX
    Explanations

    maker, -maker, person, man, ist

    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
    éĽ¾
    -0.10
    åħ«å¤§
    -0.09
    æħij
    -0.08
    åĩĨ
    -0.08
    æij
    -0.08
    èIJ¥ä¸ļ
    -0.08
    anut
    -0.08
    褶
    -0.08
    ан
    -0.08
    ROY
    -0.08
    POSITIVE LOGITS
    å¾Īå¤ļäºĭæĥħ
    0.13
    éĴĪ
    0.10
    éĢįéģ¥
    0.09
    asher
    0.09
    å¹ħ
    0.09
    çĥĺ
    0.09
    åįģ足
    0.09
    .met
    0.08
    温
    0.08
    æ´»çĿĢ
    0.08
    Activations Density 0.087%

    No Known Activations