© 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. 26465
    Prev
    Next
    INDEX
    Explanations

    oil spill prevention and response

    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
    è¾IJ
    -0.09
    æł½åŁ¹
    -0.09
    女åŃIJ
    -0.08
    糧
    -0.08
    榴
    -0.08
    对ä»ĸ
    -0.08
    è¿ijè§Ĩ
    -0.08
    .setTime
    -0.08
    è´½
    -0.08
    èĥļ
    -0.08
    POSITIVE LOGITS
    æ²¹
    0.11
    åĮĸåѦåĵģ
    0.10
     Exxon
    0.10
    æĬ¢éĻ©
    0.10
    çĨĬ
    0.10
     sÃłn
    0.10
    溢
    0.10
    oil
    0.10
    åħ¥åĽŃ
    0.10
    äºĭåıij
    0.09
    Activations Density 0.042%

    No Known Activations