© 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. 22891
    Prev
    Next
    INDEX
    Explanations

    be [word]

    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
    íķĺìĭ¤
    -0.09
    äºĶæĺŁ
    -0.08
    ROS
    -0.08
     Energ
    -0.08
    äº
    -0.08
    anders
    -0.08
     Shack
    -0.08
    ǽ
    -0.08
    Award
    -0.08
     бÑĭ
    -0.08
    POSITIVE LOGITS
     able
    0.09
    æĺİæĺİ
    0.09
    вед
    0.09
    çĪ±åĽ½ä¸»ä¹ī
    0.09
    WEEN
    0.08
    çļĦä¸Ģåijĺ
    0.08
    кÑĥÑĢ
    0.08
    æĶ¾åĩº
    0.08
    è§ĤæľĽ
    0.08
    ETA
    0.08
    Activations Density 0.164%

    No Known Activations