© 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. 18460
    Prev
    Next
    INDEX
    Explanations

    ports, holes, hooks

    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
     Lad
    -0.10
    çĻ¾ä¸ĩ
    -0.10
    èĬ·
    -0.09
    æ¼¾
    -0.09
    æ£ļ
    -0.09
    æĬ¤åį«
    -0.09
    çĶŁæĦı
    -0.09
    èݲ
    -0.09
    æĹ¥å¤ľ
    -0.09
    .AP
    -0.09
    POSITIVE LOGITS
    é£İåı£
    0.11
     ports
    0.10
    é¢ĦçķĻ
    0.10
    åŃĶ
    0.10
    å¼Ģåı£
    0.09
     holes
    0.09
    åħ¬å¸ĥçļĦ
    0.09
    éĴ©
    0.09
     hooks
    0.09
    åı£
    0.09
    Activations Density 0.258%

    No Known Activations