© 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. 55155
    Prev
    Next
    INDEX
    Explanations

    heat and temperature

    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
    åķģ
    -0.09
    è´«
    -0.09
     Hull
    -0.09
    人寿
    -0.09
    æĺµ
    -0.09
    询
    -0.09
    读æĩĤ
    -0.09
    è¿Ļæīį
    -0.09
    涮
    -0.09
     cured
    -0.08
    POSITIVE LOGITS
    åıijçĥŃ
    0.20
    æķ£çĥŃ
    0.18
     heat
    0.18
    çĥŃéĩı
    0.17
    heat
    0.17
    åįĩ温
    0.15
    Heat
    0.15
     Heat
    0.15
    åıijçĥ§
    0.13
    温度
    0.13
    Activations Density 0.084%

    No Known Activations