© 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. 34298
    Prev
    Next
    INDEX
    Explanations

    metaplasia or carcinoma

    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
    åįĹè·¯
    -0.09
    æĦ¦
    -0.08
    çĺ«
    -0.08
    对åѦçĶŁ
    -0.08
    骸
    -0.08
     ÑĨен
    -0.08
    ä¸į解
    -0.08
    æĮĤåľ¨
    -0.08
    ime
    -0.08
    éķ¿éĢĶ
    -0.08
    POSITIVE LOGITS
    转åŀĭ
    0.09
    ICollection
    0.09
    å¹½
    0.09
    .buffer
    0.09
    大夫
    0.08
    (scores
    0.08
    å¤īãĤıãĤĬ
    0.08
    athers
    0.08
    åºļ
    0.08
    .criteria
    0.08
    Activations Density 0.522%

    No Known Activations