© 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. 27547
    Prev
    Next
    INDEX
    Explanations

    just followed by a verb

    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
    é½IJ
    -0.09
    POSE
    -0.09
    INDER
    -0.09
    ä¹Łä¸įçŁ¥éģĵ
    -0.08
    ëĬIJ
    -0.08
    çļĦä¸Ģ
    -0.08
    岸
    -0.08
    å¾ĹçŁ¥
    -0.08
     tik
    -0.08
    举æĬ¥çĶµè¯Ŀ
    -0.08
    POSITIVE LOGITS
    å¹²èĦĨ
    0.16
    缴æİ¥
    0.15
    äºĨåIJ§
    0.11
     direct
    0.11
    ä¸įå¿ħ
    0.11
    è¿ĺä¸įå¦Ĥ
    0.10
    åı¯ä»¥çĽ´æİ¥
    0.10
    é£ĵ
    0.09
    åIJİèĢħ
    0.09
    ç®ĹäºĨ
    0.09
    Activations Density 0.066%

    No Known Activations