© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6955
    Prev
    Next
    INDEX
    Explanations

    when then

    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
    åĪ«è¯´
    -0.11
    为æĤ¨
    -0.10
    dale
    -0.10
    ä¸ļ
    -0.10
    èµ°å¾Ĺ
    -0.09
    çļĦä¸ĢéĿ¢
    -0.09
    StackSize
    -0.09
    为æĤ¨æıIJä¾Ľ
    -0.09
     OVERRIDE
    -0.08
    æ¯Ķè¾ĥå¤ļ
    -0.08
    POSITIVE LOGITS
    rys
    0.08
    åŃª
    0.08
    蹶
    0.08
     ìłģ
    0.08
    èĥ½ä½¿
    0.08
    ellas
    0.08
    缮çļĦæĺ¯
    0.08
    å¬ī
    0.08
    ç¬ijè¯Ŀ
    0.07
    åıĤè°ĭ
    0.07
    Activations Density 0.325%

    No Known Activations