© 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. 50792
    Prev
    Next
    INDEX
    Explanations

    exaggeration or intensification

    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
    éķ¿å¾Ĺ
    -0.09
    å°±åºĶ该
    -0.09
    SCO
    -0.09
    åķ¡
    -0.08
    å¾Ĺå¾Ī好
    -0.08
     hart
    -0.08
    åŃIJéĩĮ
    -0.08
    å°±ä¸įä¼ļ
    -0.08
    çī¯
    -0.08
    æĮģãģ¡
    -0.08
    POSITIVE LOGITS
    ãģķãĤīãģ«
    0.14
    è¿Ľä¸ĢæŃ¥
    0.12
     worse
    0.11
     Worse
    0.11
    åĬłä¹ĭ
    0.11
    ãģķãĤī
    0.11
    è¿ĺè¦ģ
    0.11
    åĨįåĬłä¸Ĭ
    0.11
    ä¸įä»ħå¦ĤæѤ
    0.10
     further
    0.10
    Activations Density 0.023%

    No Known Activations