© 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. 6350
    Prev
    Next
    INDEX
    Explanations

    equal treatment

    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
    讹
    -0.11
    glomer
    -0.10
    审
    -0.09
    çŃ¾ç½²
    -0.09
    çŃ¾ç½²äºĨ
    -0.09
     conv
    -0.09
    诵
    -0.09
    esto
    -0.09
    æ¶Īè´¹èĢħçļĦ
    -0.08
    ãģ¾ãģ¾
    -0.08
    POSITIVE LOGITS
    æѧè§Ĩ
    0.10
    ç»ıçIJĨ
    0.09
    æĭĶ
    0.09
    åĨħåľ°
    0.09
    apon
    0.08
    åĵ©
    0.08
    ä¸ĢåĪ»
    0.08
    GREE
    0.08
    allen
    0.08
    èĥĸåŃIJ
    0.08
    Activations Density 0.061%

    No Known Activations