© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7850
    Prev
    Next
    INDEX
    Explanations

    autoimmune 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
    èIJ½åı¶
    -0.10
    éĢĨè¡Į
    -0.09
    oid
    -0.09
    åıĭåĸĦ
    -0.08
    çĥŃçĪ±
    -0.08
    влаж
    -0.08
    äºĶ大
    -0.08
     Trib
    -0.08
     trib
    -0.08
    é«ĺæ¡£
    -0.08
    POSITIVE LOGITS
    ç¥ł
    0.09
    éĤ¯
    0.09
    滩
    0.09
    娶
    0.08
    ipline
    0.08
    ç¥Ł
    0.08
    åİĨåı²ä¸Ĭ
    0.08
    agna
    0.08
    ä½ĵåĬĽ
    0.08
    产
    0.08
    Activations Density 0.464%

    No Known Activations