© 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. 30211
    Prev
    Next
    INDEX
    Explanations

    executive followed by title

    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
    使çĶ¨æĿĥ
    -0.09
    ä¸įèī¯
    -0.09
    tures
    -0.09
    ä¸Ńå°ıåŀĭ
    -0.08
    大åıĶ
    -0.08
    IED
    -0.08
    xo
    -0.08
    常å§Ķä¼ļ
    -0.08
    éĩįçĤ¹é¢ĨåŁŁ
    -0.08
    çİĩåħĪ
    -0.08
    POSITIVE LOGITS
     Downs
    0.10
    лей
    0.10
    åĪ°ä½į
    0.09
    laÅŁ
    0.09
    ailed
    0.09
    åıĤèĢĥèµĦæĸĻ
    0.09
    éķĸ
    0.09
    æ²Ļæ¼ł
    0.09
    ãĢħ
    0.09
    orde
    0.08
    Activations Density 0.007%

    No Known Activations