© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36879
    Prev
    Next
    INDEX
    Explanations

    expenses and costs

    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
    殿
    -0.09
    æĸ©
    -0.09
    ustin
    -0.09
     бил
    -0.09
    å¥ĭ
    -0.09
     lord
    -0.08
    otti
    -0.08
    ulin
    -0.08
    ibel
    -0.08
    纪
    -0.08
    POSITIVE LOGITS
    è´¹çĶ¨
    0.16
    è²»çĶ¨
    0.15
     costs
    0.13
     cost
    0.13
    èĬ±è´¹
    0.13
     expenses
    0.13
    åħįè´¹
    0.13
    çļĦæĪIJæľ¬
    0.12
    æĪIJæľ¬
    0.12
     kosten
    0.12
    Activations Density 0.041%

    No Known Activations