© 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. 4790
    Prev
    Next
    INDEX
    Explanations

    first met or meeting

    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
    å°Ĩèĩªå·±çļĦ
    -0.09
    INGER
    -0.09
    溷
    -0.08
    æĶ¯éħį
    -0.08
    çĥŃçĤ¹
    -0.08
    åįģäºĮäºĶ
    -0.08
    座
    -0.08
    learner
    -0.08
    ovie
    -0.08
     Bott
    -0.08
    POSITIVE LOGITS
    缸è¯Ĩ
    0.20
    缸éģĩ
    0.16
    缸è§ģ
    0.15
    è§ģéĿ¢
    0.15
    éĤĤ
    0.14
     meeting
    0.13
     meet
    0.13
    åĩºä¼ļãģĦ
    0.13
     вÑģÑĤÑĢеÑĩ
    0.13
    æݥ触
    0.13
    Activations Density 0.068%

    No Known Activations