© 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. 23208
    Prev
    Next
    INDEX
    Explanations

    oil and gas extraction/policy

    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
    éĽħ
    -0.11
    ä»įæľª
    -0.09
    è´«è¡Ģ
    -0.09
     Owen
    -0.09
     Patton
    -0.08
    ç²īä¸Ŀ
    -0.08
    uck
    -0.08
     ÅŁiddet
    -0.08
    ucas
    -0.08
    apat
    -0.08
    POSITIVE LOGITS
    çŁ³æ²¹
    0.15
    油价
    0.14
     oil
    0.14
    åİŁæ²¹
    0.13
    Oil
    0.13
    大åºĨ
    0.13
     Oil
    0.12
    åĤ¨éĩı
    0.12
    èĥ½æºIJ
    0.12
    æ²¹
    0.12
    Activations Density 0.117%

    No Known Activations