© 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. 61598
    Prev
    Next
    INDEX
    Explanations

    cardio and energy expenditure

    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
    åĮĸèĤ¥
    -0.10
    éļĶ离
    -0.08
    èĥĮ
    -0.08
    鸳
    -0.08
    åħ
    -0.08
    ave
    -0.08
    inde
    -0.08
    åı°è¯į
    -0.08
     isolated
    -0.08
    åĶ¯ä¸ĢçļĦ
    -0.08
    POSITIVE LOGITS
    æĮģä¹ħ
    0.10
    仪
    0.09
    éķ¿ä¹ħ
    0.09
    از
    0.09
    acular
    0.09
    åºķéĥ¨
    0.09
    ç»Į
    0.09
    å¹³åİŁ
    0.08
    丽
    0.08
    Pros
    0.08
    Activations Density 0.073%

    No Known Activations