© 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. 16985
    Prev
    Next
    INDEX
    Explanations

    capital investment 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
    æķ¬ä¸ļ
    -0.11
    è¾ħ导
    -0.10
    é©»
    -0.10
    帮åĬ©ä¼ģä¸ļ
    -0.09
    对åħ¶
    -0.09
    ä»İ严
    -0.09
    åľºä¸Ĭ
    -0.09
    è¼Ķ
    -0.09
    èĥĮçĿĢ
    -0.09
    è´´
    -0.09
    POSITIVE LOGITS
    设å¤ĩ
    0.11
    å§ĭ
    0.10
     capital
    0.10
    equipment
    0.10
     обоÑĢÑĥд
    0.09
     costs
    0.09
    æĪIJæľ¬
    0.09
    spir
    0.09
     equipment
    0.09
     обоÑĢÑĥдованиÑı
    0.09
    Activations Density 0.175%

    No Known Activations