© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 569
    Prev
    Next
    INDEX
    Explanations

    monopoly position

    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
    Negative Logits
    åįģä¸ĩ
    -0.12
    íĩ´
    -0.09
    èĩªåѦ
    -0.09
    å»īä»·
    -0.09
    ç¾Ĭ
    -0.09
    è¥Ħ
    -0.08
    .Tools
    -0.08
    çĹĴ
    -0.08
    ita
    -0.08
    æªĢ
    -0.08
    POSITIVE LOGITS
    åŀĦæĸŃ
    0.13
    åŀ
    0.12
     monopol
    0.11
    导
    0.11
    åŀĦ
    0.11
    ç»ķ
    0.10
    å£
    0.10
    å°İ
    0.10
    åĬ¿åĬĽ
    0.10
    å¸Ŀ
    0.10
    Activations Density 0.087%

    No Known Activations