© 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. 3939
    Prev
    Next
    INDEX
    Explanations

    cheating people or consumers

    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
    çļĦåĪ°æĿ¥
    -0.10
    ä½łåĸľæ¬¢
    -0.09
    ä¸ĭåįĪ
    -0.09
    åĢ¦
    -0.09
    çļĦéŃħåĬĽ
    -0.09
    éļ¨æĻĤ
    -0.09
    èģĮ
    -0.09
    ousel
    -0.09
    leased
    -0.09
    è´¿
    -0.09
    POSITIVE LOGITS
    æ·³
    0.10
     naive
    0.09
    å°ijåIJĥ
    0.08
    èĢģå®ŀ
    0.08
    åĪ©çĽĬ
    0.08
    åIJĥäºı
    0.08
    inch
    0.08
    nga
    0.08
    轻微
    0.08
    okit
    0.08
    Activations Density 0.043%

    No Known Activations