© 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. 52470
    Prev
    Next
    INDEX
    Explanations

    fluid dynamics flow

    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
    åħħ
    -0.10
    æ§Į
    -0.09
    æĪ¿åŃIJ
    -0.09
    æŁ¥çľĭæĽ´å¤ļ
    -0.09
    éļ¾åħį
    -0.08
    ëį°ìĿ´
    -0.08
     pearls
    -0.08
    éŃĤ
    -0.08
    brick
    -0.08
    æĬ½
    -0.08
    POSITIVE LOGITS
    æ¹į
    0.11
    æ°´æµģ
    0.10
     flow
    0.10
    é£İæ°Ķ
    0.10
     airflow
    0.09
    (flow
    0.09
    etti
    0.09
     fluid
    0.09
    æµģ
    0.09
    å¯ĨéĽĨ
    0.09
    Activations Density 0.166%

    No Known Activations