© 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. 18733
    Prev
    Next
    INDEX
    Explanations

    refrigerator, fridge, freezer, temperatures, low, cold

    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
    ä¸įæĸ¹ä¾¿
    -0.10
    é¹Ĭ
    -0.10
    滹
    -0.09
    姿åĬ¿
    -0.09
    æĻĸ
    -0.09
    è±Ĩçĵ£
    -0.09
    èµŃ
    -0.09
    åģļä¸Ģ个
    -0.09
    \Abstract
    -0.08
    ohon
    -0.08
    POSITIVE LOGITS
    åĨ·èĹı
    0.20
    åĪ¶åĨ·
    0.18
    åĨ·åĨ»
    0.17
    åĨ°ç®±
    0.16
     refrigerator
    0.16
     refriger
    0.15
     Chill
    0.14
    åĨ°
    0.14
     freezer
    0.14
    åĨ·åºĵ
    0.13
    Activations Density 0.215%

    No Known Activations