© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20032
    Prev
    Next
    INDEX
    Explanations

    narcotic drug prescriptions and treatment

    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
    soles
    -0.10
    irst
    -0.09
    éĴĹ
    -0.09
    biased
    -0.08
    ç½¹
    -0.08
    é½
    -0.08
    еÑĢÑĤ
    -0.08
    _WM
    -0.08
    è¿ĩåħ³
    -0.08
    vier
    -0.08
    POSITIVE LOGITS
    麻
    0.09
    åī©
    0.09
     pozosta
    0.08
    æī£
    0.08
    hive
    0.08
    ç½²
    0.08
    sms
    0.08
     phẩm
    0.08
    åī©ä¸ĭçļĦ
    0.08
    _frontend
    0.08
    Activations Density 0.030%

    No Known Activations