© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47480
    Prev
    Next
    INDEX
    Explanations

    `valid`, `injury`, `old`, `iking`, `Pay`

    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
    Negative Logits
    åĬĽè¿ĺæĺ¯
    -0.11
    ãģ§ãģĻãģĹ
    -0.10
    ãģłãģĹ
    -0.10
     lắm
    -0.09
    ä¹Łå¥½
    -0.09
    楼å±Ĥ
    -0.09
    ãĢįãĢĮ
    -0.09
    ï¼īãĢģ
    -0.08
    çĨŁæĤīçļĦ
    -0.08
    å²ļ
    -0.08
    POSITIVE LOGITS
     finale
    0.10
    çŃīçŃī
    0.09
    æľĢåIJİä¸Ģ
    0.09
    æľĢå¾Į
    0.09
    ãģªãģ©
    0.08
     miscellaneous
    0.08
    æľĢåIJİ
    0.08
    umped
    0.08
    overall
    0.08
    ersh
    0.08
    Activations Density 0.338%

    No Known Activations