© 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. 55917
    Prev
    Next
    INDEX
    Explanations

    mining, agriculture, land use, environmental conflicts

    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
    åºŁæŧ
    -0.10
    åºŁ
    -0.10
    廢
    -0.09
    åĿļæŀľ
    -0.09
    çļĦ妻åŃIJ
    -0.09
    æ¡ī
    -0.09
    èIJ¥
    -0.09
     ullam
    -0.09
    说åĩºæĿ¥
    -0.09
     überh
    -0.09
    POSITIVE LOGITS
    ç¨Ģ
    0.09
    æľªæĿ¥åıijå±ķ
    0.09
    ä¸ĩä¸Ģ
    0.09
    æľ¬æĿ¥å°±
    0.09
    vals
    0.08
     gag
    0.08
    ä¸ĩ
    0.08
    è¡Į人
    0.08
    (dl
    0.08
    驶
    0.08
    Activations Density 0.071%

    No Known Activations