© 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. 48510
    Prev
    Next
    INDEX
    Explanations

    insulation, conductivity, warmth, invention

    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
     Atmos
    -0.10
    åŃķ
    -0.09
    (Of
    -0.09
    è§Ĭ
    -0.09
     atmos
    -0.09
    åģıåģı
    -0.09
    为ä¸Ģä½ĵ
    -0.09
    éĺķ
    -0.09
    éªŁ
    -0.09
    å´Ľ
    -0.09
    POSITIVE LOGITS
    éļĶçĥŃ
    0.11
    æķĪæŀľ
    0.09
    å¢Ļä½ĵ
    0.09
    æĿ¿æĿIJ
    0.09
    表çİ°
    0.09
    åłµå¡ŀ
    0.08
     factory
    0.08
    -stars
    0.08
     insulation
    0.08
    æĿIJ
    0.08
    Activations Density 0.063%

    No Known Activations