© 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. 23197
    Prev
    Next
    INDEX
    Explanations

    economics and economic terms

    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
    ties
    -0.09
    ForResult
    -0.09
    éĩijéĻµ
    -0.08
    aneously
    -0.08
    bage
    -0.08
    ç¼ij
    -0.08
    å¿ĥè¡Ģ
    -0.08
    æİĩ
    -0.08
    erot
    -0.08
    çĿ«
    -0.08
    POSITIVE LOGITS
    æľ¯è¯Ń
    0.10
    ç»ıæµİåѦ
    0.09
    itur
    0.09
    -economic
    0.08
    /big
    0.08
    ãģªãĤĭ
    0.08
    åįģæĿ¡
    0.08
    stuff
    0.08
    owell
    0.08
    çī¡ä¸¹
    0.08
    Activations Density 0.015%

    No Known Activations