© 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. 19318
    Prev
    Next
    INDEX
    Explanations

    pathogen virus infections and diseases

    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
    åģļå¾Ĺ
    -0.10
    åıį对
    -0.09
    enha
    -0.09
    åį¦
    -0.09
    аÑħ
    -0.09
    åĩłä½ķ
    -0.09
    伤çĹħ
    -0.08
    èĮ´
    -0.08
    æ®Ĩ
    -0.08
    adem
    -0.08
    POSITIVE LOGITS
    æĹłæĥħ
    0.10
    æİĮ
    0.09
    åŃĺåľ¨äºİ
    0.09
    otted
    0.08
    æľīèĥ½åĬĽ
    0.08
    渡
    0.08
    çĶŁåij½åĬĽ
    0.08
    à¸ļรร
    0.08
    ä¸ĢçĤ¹çĤ¹
    0.08
    å·¢
    0.08
    Activations Density 0.195%

    No Known Activations