© 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. 5839
    Prev
    Next
    INDEX
    Explanations

    as if

    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
     Weiss
    -0.10
    antz
    -0.09
    ÑĪин
    -0.09
    ìĸ¼
    -0.09
    ä¾Ī
    -0.09
    åĩ¡
    -0.08
    è¡·
    -0.08
    ä¼ģä¸ļæıIJä¾Ľ
    -0.08
    åħ³éĶ®æĺ¯
    -0.08
     vern
    -0.08
    POSITIVE LOGITS
    置身
    0.13
    对å¾ħ
    0.10
    å°±åĥıæĺ¯
    0.10
    åĥıæĺ¯
    0.10
    æĺ¯è¦ģ
    0.10
    åIJİæŀľ
    0.10
    æĺ¯åľ¨
    0.10
    æĽ´åĥıæĺ¯
    0.09
    å°ĨæĿ¥
    0.09
    èŁ¾
    0.09
    Activations Density 0.018%

    No Known Activations