© 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. 56416
    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
    åŁİåĮº
    -0.08
    身ä¸Ĭ
    -0.08
    åĪ«äºº
    -0.08
    å«Į
    -0.08
    è¡Ĺ
    -0.08
    éĵº
    -0.08
    çĪ±å¥½
    -0.08
    åŁİéĩĮ
    -0.08
    æ³ķ人
    -0.08
    obi
    -0.07
    POSITIVE LOGITS
    ç³»ç»ŁçļĦ
    0.16
     system
    0.15
    ç³»ç»Ł
    0.14
     ÑģиÑģÑĤема
    0.14
    系統
    0.13
    system
    0.13
     ÑģиÑģÑĤемÑĭ
    0.13
     sistema
    0.13
    ãĤ·ãĤ¹ãĥĨãĥł
    0.12
     système
    0.12
    Activations Density 0.104%

    No Known Activations