© 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. 22903
    Prev
    Next
    INDEX
    Explanations

    prescribed medications

    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
    åİ¥
    -0.09
    adle
    -0.08
    .gc
    -0.08
    ä¸Ģ个个
    -0.08
    phasis
    -0.08
    fixture
    -0.08
    ItemSelected
    -0.08
     deg
    -0.08
    丰å¯Įå¤ļ彩
    -0.08
    æ²ī浸
    -0.08
    POSITIVE LOGITS
    å¸ĤéĿ¢ä¸Ĭ
    0.11
    çķħéĶĢ
    0.10
    åī¯ä½ľçĶ¨
    0.10
    å¸Ĥåľºä¸Ĭ
    0.10
     пÑĢепаÑĢаÑĤ
    0.10
    åĵģçīĮ
    0.10
    åľ¨å¸Ĥåľºä¸Ĭ
    0.10
    说æĺİ书
    0.09
     brand
    0.09
    åIJĮç±»
    0.09
    Activations Density 0.335%

    No Known Activations