© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60816
    Prev
    Next
    INDEX
    Explanations

    economic costs and impact

    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
    Negative Logits
    æĬĬæݧ
    -0.10
    åį±
    -0.10
    妫
    -0.08
    çģ¾åĮº
    -0.08
    éĴ»
    -0.08
    书åºĹ
    -0.08
    bler
    -0.08
    åį±éĻ©
    -0.08
     Hacker
    -0.08
    èĵ¦
    -0.08
    POSITIVE LOGITS
     costs
    0.10
    æĪIJæľ¬
    0.10
    çĶŁäº§åĬĽ
    0.09
    缺å¸Ń
    0.09
     productivity
    0.09
    ERO
    0.09
     cost
    0.09
    æĥĬ人
    0.08
    èĩªçIJĨ
    0.08
    -cost
    0.08
    Activations Density 0.088%

    No Known Activations