© 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. 20347
    Prev
    Next
    INDEX
    Explanations

    x-ray and radiation

    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
    åĶ±
    -0.09
    天ä¸ĭ
    -0.09
    åĪĪ
    -0.09
    æįı
    -0.08
     Sask
    -0.08
     traumat
    -0.08
    åŃĽ
    -0.08
    strument
    -0.08
    éĢŁ
    -0.08
    å¹³åĿĩæ¯ı
    -0.08
    POSITIVE LOGITS
    ona
    0.09
    ONA
    0.09
     болÑĮ
    0.09
    ä¸Ģ次æĢ§
    0.08
    æĢª
    0.08
    incident
    0.08
    èµĸ
    0.08
    ä¸Ģç¬ij
    0.08
    æĦŁåºĶ
    0.08
    ANTED
    0.08
    Activations Density 0.164%

    No Known Activations