© 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. 48623
    Prev
    Next
    INDEX
    Explanations

    past participle after been

    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
    人身
    -0.09
    лин
    -0.09
    æĪ¿
    -0.09
    åĬŀå®ŀäºĭ
    -0.08
     Manufact
    -0.08
    âĦħ
    -0.08
    ä»ĸçŁ¥éģĵ
    -0.08
     OnTrigger
    -0.08
    æľīä¿¡å¿ĥ
    -0.08
    åłķ
    -0.08
    POSITIVE LOGITS
    æķ´
    0.10
    èµģ
    0.09
    ç½ij讯
    0.09
    çĽ¯
    0.09
    sembles
    0.09
    ç¢Į
    0.08
    èĭ¦
    0.08
    stras
    0.08
    rones
    0.08
    æģ¶å¿ĥ
    0.08
    Activations Density 0.058%

    No Known Activations