© 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. 31701
    Prev
    Next
    INDEX
    Explanations

    immune response to antigens

    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
     buck
    -0.10
    ä¸¤å¼ł
    -0.10
    è¾ij
    -0.09
    端æŃ£
    -0.09
    ascript
    -0.08
    ende
    -0.08
    èĥŀ
    -0.08
    éħįå¥Ĺ设æĸ½
    -0.08
    epam
    -0.08
    横åIJij
    -0.08
    POSITIVE LOGITS
    odge
    0.09
    æ½ľ
    0.09
    resenter
    0.09
    iard
    0.09
    _FLAG
    0.08
    enburg
    0.08
    åĩºçīĪ社
    0.08
    ä¸Ģ次次
    0.08
     amat
    0.08
    andez
    0.08
    Activations Density 0.337%

    No Known Activations