© 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. 30648
    Prev
    Next
    INDEX
    Explanations

    real estate, realtor, professional services

    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
    èĺ¸
    -0.12
    çĶŁäº§å·¥èīº
    -0.10
    çĶŁäº§è½¦éĹ´
    -0.09
    åľ°çIJĥä¸Ĭ
    -0.09
    msp
    -0.09
    orer
    -0.09
    æıIJèµ·
    -0.08
    èī¾æ»ĭ
    -0.08
    æ¿Ģ
    -0.08
    æ¿ł
    -0.08
    POSITIVE LOGITS
    æĪ¿åľ°äº§
    0.14
     Realty
    0.14
    è´ŃæĪ¿
    0.13
    æĪ¿äº§
    0.13
     MLS
    0.13
    æĪ¿æºIJ
    0.13
    æĪ¿ä»·
    0.13
    楼çĽĺ
    0.12
    æĪIJ交
    0.12
    é£İæ°´
    0.11
    Activations Density 0.172%

    No Known Activations