© 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. 30782
    Prev
    Next
    INDEX
    Explanations

    administr", "sent", "buried", "arrangement"

    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
    åĪ¹
    -0.09
    æIJŀ
    -0.09
    uga
    -0.09
    achable
    -0.08
     Mü
    -0.08
    åıijçĶŁçļĦ
    -0.08
    èģĺçĶ¨
    -0.08
    éĢĤçĶ¨
    -0.08
    ä¹łæĥ¯
    -0.08
    xbb
    -0.08
    POSITIVE LOGITS
    æĢĴ
    0.09
    享
    0.09
     phủ
    0.09
    uml
    0.08
    lek
    0.08
     LAP
    0.08
    æī©
    0.08
    å°Ĩè¿Ľä¸ĢæŃ¥
    0.08
    éĦ±
    0.08
    å¹Ľ
    0.08
    Activations Density 0.005%

    No Known Activations