© 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. 23421
    Prev
    Next
    INDEX
    Explanations

    dioceses and bishops

    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
    åŃķ
    -0.10
    åĬłå¿«å»ºè®¾
    -0.09
     Salisbury
    -0.09
    触
    -0.09
    æĿij
    -0.09
    çłģ
    -0.08
     exped
    -0.08
     Stout
    -0.08
    огÑĢам
    -0.08
    å§IJ
    -0.08
    POSITIVE LOGITS
    owie
    0.09
    ð«
    0.09
    ms
    0.08
    æİ°
    0.08
    身æĿIJ
    0.08
    å¤ĸç±į
    0.08
     confort
    0.08
    æij§
    0.08
    管è¾ĸ
    0.08
     mess
    0.08
    Activations Density 0.054%

    No Known Activations