© 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. 7628
    Prev
    Next
    INDEX
    Explanations

    to do

    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
    orr
    -0.09
     Kv
    -0.08
    ez
    -0.07
    \xa
    -0.07
    çŃĸ
    -0.07
    大æ´ĭ
    -0.07
     Bell
    -0.07
    ãģ®ãģĬ
    -0.07
    èĽĽ
    -0.07
    4
    -0.07
    POSITIVE LOGITS
     ÙĪاÙĦØ°ÙĬ
    0.11
    æīĢæıIJä¾Ľ
    0.11
    ä¼ģä¸ļæıIJä¾Ľ
    0.11
    æıIJä¾Ľä¼ĺè´¨
    0.11
    å±ħçĦ¶
    0.10
    åħīæºIJ
    0.10
     ÙĪاÙĦتÙĬ
    0.10
    鼳
    0.10
    opus
    0.10
    çªģåĩºéĹ®é¢ĺ
    0.10
    Activations Density 0.432%

    No Known Activations