© 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. 53959
    Prev
    Next
    INDEX
    Explanations

    drug interactions medication azole opioids

    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
    éĶĢ
    -0.08
    课åłĤæķĻåѦ
    -0.08
    onomy
    -0.08
     prz
    -0.08
    idis
    -0.08
    gart
    -0.08
    æĽ²æĬĺ
    -0.08
    elia
    -0.08
    (DIS
    -0.08
    _Instance
    -0.07
    POSITIVE LOGITS
    ä»»ä½ķå½¢å¼ı
    0.12
    åIJĮæĻĤãģ«
    0.10
    ä¼ļ产çĶŁ
    0.09
     íĺ¹
    0.09
    éĤ£è¾¹
    0.09
    feeds
    0.09
    æĹłæĦı
    0.09
    åIJĮæŶè¿ĺ
    0.09
     UIB
    0.09
    ä¸İæѤåIJĮæŶ
    0.08
    Activations Density 0.118%

    No Known Activations