© 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. 29484
    Prev
    Next
    INDEX
    Explanations

    amarillo, ghetto, brokeback mountain

    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
    俱
    -0.09
    iting
    -0.09
    .fixture
    -0.08
    飨
    -0.08
    æĺĨ
    -0.08
    GIT
    -0.08
    ä¸īæĿ¡
    -0.08
    -0.08
    _CHANNEL
    -0.07
    åľ¨ä»ĸçļĦ
    -0.07
    POSITIVE LOGITS
    让大家
    0.11
    绫
    0.10
    纵åIJij
    0.10
    zelf
    0.09
    æĿµ
    0.09
    æĥ³ä¸įåĪ°
    0.09
    burger
    0.09
    enant
    0.09
    åĵĩ
    0.09
    æĹłçŁ¥
    0.09
    Activations Density 0.001%

    No Known Activations