© 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. 39309
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æµ·åºķ
    -0.09
    èµĦæºIJåħ±äº«
    -0.09
    åģļ好
    -0.09
    éĦ£
    -0.09
    代价
    -0.08
    åľ»
    -0.08
    .createComponent
    -0.08
    adle
    -0.08
    éĽ¹
    -0.08
    æĮĩå¼ķ
    -0.08
    POSITIVE LOGITS
    æķ¦
    0.09
    ulus
    0.08
    çļĦåIJĮæŶ
    0.08
    peg
    0.08
     EITHER
    0.07
    asy
    0.07
    ago
    0.07
    èģĨåIJ¬
    0.07
    åºĶæĢ¥ç®¡çIJĨ
    0.07
    á¿Ĩ
    0.07
    Activations Density 0.000%

    No Known Activations