© 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. 63199
    Prev
    Next
    INDEX
    Explanations

    Deepwater Horizon disaster

    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
    æĭ¬
    -0.09
     saddle
    -0.09
    asca
    -0.08
    èijĹä½ľæĿĥ
    -0.08
     Bris
    -0.08
    -components
    -0.08
    çª
    -0.08
    èĻļ
    -0.08
    \core
    -0.08
    订éĺħ
    -0.08
    POSITIVE LOGITS
    éĩį建
    0.10
    使çĶ¨çļĦ
    0.09
    aset
    0.09
    ä¸IJ
    0.08
    ä¸Ģçīĩ
    0.08
    ä¸ĸçķĮ级
    0.08
    ç©¿éĢı
    0.08
    çļĦæľĭåıĭ
    0.08
    éĢłæĪIJçļĦ
    0.08
    æľīä»·åĢ¼
    0.08
    Activations Density 0.009%

    No Known Activations