© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20170
    Prev
    Next
    INDEX
    Explanations

    steel mill production

    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
     Second
    -0.09
    lbrace
    -0.09
    åŁ¹
    -0.08
    pora
    -0.08
    è´µ
    -0.08
     disgr
    -0.08
    éħĴç²¾
    -0.08
    าย
    -0.08
     ev
    -0.08
    æŀľ
    -0.08
    POSITIVE LOGITS
    éĴ¢æĿIJ
    0.17
    éĴ¢åİĤ
    0.15
    éĴ¢éĵģ
    0.15
    轧
    0.14
    éĴ¢
    0.13
    éĭ¼
    0.12
     steel
    0.12
    éĴ¢æĿ¿
    0.12
    éĶ»
    0.12
    åĨ¶éĩij
    0.12
    Activations Density 0.087%

    No Known Activations