© 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. 57548
    Prev
    Next
    INDEX
    Explanations

    heat sink, fan, cooling, die, hot

    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
    æĢĨ
    -0.10
    ç»Ĺ
    -0.10
    é¹Ħ
    -0.10
    ä¸ŃéĢĶ
    -0.09
    è¯ģåĪ¸äº¤æĺĵ
    -0.09
    æĺİç»Ĩ
    -0.09
    ntl
    -0.09
    ä¼¥
    -0.09
    ceptors
    -0.09
    潦
    -0.09
    POSITIVE LOGITS
    æķ£çĥŃ
    0.12
     Blur
    0.08
     heat
    0.08
    å°ģè£ħ
    0.08
    座
    0.08
    Blur
    0.07
    æĮº
    0.07
     diss
    0.07
    许
    0.07
    åŁł
    0.07
    Activations Density 0.137%

    No Known Activations