© 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. 7328
    Prev
    Next
    INDEX
    Explanations

    verbs followed by complements

    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
    çĶ¨èĩªå·±çļĦ
    -0.10
     Yourself
    -0.09
    è¿Ļä¹Ł
    -0.09
    èĩªå·±çļĦ
    -0.09
    éĢIJå¹´
    -0.08
    è¿Ļä¹Łæĺ¯
    -0.08
    è¿Ļå°±
    -0.08
    Ñĩин
    -0.08
    以æѤ
    -0.08
     Ñģебе
    -0.08
    POSITIVE LOGITS
     Ñģобой
    0.11
    äºĨæĪijçļĦ
    0.11
    æĪij没
    0.10
    opp
    0.10
    æĪijè¦ģ
    0.09
    æĪijå¸ĮæľĽ
    0.09
    ä»İæł¹æľ¬ä¸Ĭ
    0.09
    æľ¬æĿ¥
    0.09
    æĪij们
    0.09
    æĪij们å¿ħé¡»
    0.09
    Activations Density 0.325%

    No Known Activations