© 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. 49451
    Prev
    Next
    INDEX
    Explanations

    immune system

    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
    身åIJİ
    -0.10
    entai
    -0.10
    çļĦå±ĢéĿ¢
    -0.09
    称ä¹ĭ为
    -0.09
    å¤ĸåĽ´
    -0.09
    æľīèī²
    -0.09
    åĨ¶éĩij
    -0.08
    lettes
    -0.08
    oken
    -0.08
     glaring
    -0.08
    POSITIVE LOGITS
    atics
    0.09
    ä¸ĵ线
    0.09
    isle
    0.09
    æĦ¿æľĽ
    0.08
    åı¯æĥ³èĢĮçŁ¥
    0.08
    (SIG
    0.08
    دÙĪÙĨ
    0.08
    ycz
    0.08
    ucz
    0.08
     Quart
    0.08
    Activations Density 0.052%

    No Known Activations