© 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. 5597
    Prev
    Next
    INDEX
    Explanations

    arterial pressure and blood 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
     pattern
    -0.09
    çĶ³
    -0.09
     Lena
    -0.09
    èľķåıĺ
    -0.08
    æĸĩæĺİ
    -0.08
    irting
    -0.08
    èĽ
    -0.08
    ä¿ı
    -0.08
    par
    -0.08
     UNS
    -0.08
    POSITIVE LOGITS
    åİĭåĬĽ
    0.11
    çļĦåİĭåĬĽ
    0.10
    豺
    0.09
    æºī
    0.09
     pressures
    0.09
    pressure
    0.09
    å£ĵåĬĽ
    0.08
    éĬ®
    0.08
    å°Ķæĸ¯
    0.08
     ÐŃÑĤ
    0.08
    Activations Density 0.302%

    No Known Activations