© 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. 33093
    Prev
    Next
    INDEX
    Explanations

    air conditioning and HVAC systems

    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
     resc
    -0.10
    ä¸Ģ举
    -0.09
    å±ģ
    -0.09
    缨
    -0.08
     Rescue
    -0.08
    éĺµåľ°
    -0.08
    Gear
    -0.08
    鼷
    -0.08
    æľĢå¿«
    -0.08
    æĶ¶åĽŀ
    -0.08
    POSITIVE LOGITS
    ä¸Ń央空è°ĥ
    0.11
    üst
    0.10
     Beard
    0.09
    æĦŁ
    0.09
    æľºç»Ħ
    0.09
    åįİ侨
    0.09
    éĻIJæľŁ
    0.09
    æĿ¡è¯Ħ论
    0.09
    dirty
    0.09
    .react
    0.09
    Activations Density 0.084%

    No Known Activations