© 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. 57886
    Prev
    Next
    INDEX
    Explanations

    list items

    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
    éĩĩçĶ¨äºĨ
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    åľ¨è¿Ļ
    -0.08
    ãģĦãģĨ
    -0.08
    olib
    -0.08
    AMS
    -0.07
    æĿ¥è¯´
    -0.07
    å¤ļä¹Ī
    -0.07
    èĩªçĦ¶èĢĮ
    -0.07
    çļĦæĺ¯
    -0.07
    POSITIVE LOGITS
     etc
    0.14
    çŃīçŃī
    0.12
    以åıĬ
    0.12
    çŃīåĽłç´ł
    0.11
    çŃīæĸ¹éĿ¢
    0.11
    ãģĿãģĹãģ¦
    0.11
     ëĵ±ìĿĦ
    0.11
     ê·¸ë¦¬ê³ł
    0.11
    çŃīåĨħ容
    0.11
    çŃīæĸ¹éĿ¢çļĦ
    0.11
    Activations Density 0.727%

    No Known Activations