© 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. 22437
    Prev
    Next
    INDEX
    Explanations

    traffic issues

    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
    ä¸Ģ举
    -0.10
    hood
    -0.10
    Dur
    -0.10
    íĴĪ
    -0.10
    åĪ°æĿ¥
    -0.09
     Opr
    -0.09
    erate
    -0.09
    家乡
    -0.09
    ä¸ĸçķĮ级
    -0.09
    æ°ijæĶ¿å±Ģ
    -0.09
    POSITIVE LOGITS
    rets
    0.10
    .utility
    0.10
    -economic
    0.08
     literacy
    0.08
    çݯå¢ĥåį«çĶŁ
    0.08
    onom
    0.08
    漪
    0.08
    Endian
    0.08
    ед
    0.07
    åIJĮ缣
    0.07
    Activations Density 0.009%

    No Known Activations