© 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. 16996
    Prev
    Next
    INDEX
    Explanations

    names of people

    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
    å¾®éĩı
    -0.09
    è¾ľè´Ł
    -0.09
    æĢ»ä½ĵ
    -0.09
     skim
    -0.08
    åģľçķĻ
    -0.08
    头顶
    -0.08
    Bush
    -0.08
    üc
    -0.08
     bush
    -0.08
     misses
    -0.08
    POSITIVE LOGITS
    èĢģ人
    0.11
    çĭĹ
    0.09
     доволÑĮ
    0.09
    linkplain
    0.09
    æŀĦ件
    0.09
     Duffy
    0.09
    离éĢĢä¼ij
    0.09
    QUIT
    0.09
    orting
    0.09
    -Jun
    0.08
    Activations Density 0.024%

    No Known Activations