© 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. 50400
    Prev
    Next
    INDEX
    Explanations

    drug approval and regulatory processes

    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
    æĪĴ
    -0.09
     remar
    -0.09
    åĺ±
    -0.09
    å¾ĭ
    -0.08
    èŀįåIJĪ
    -0.08
    odem
    -0.08
    ableObject
    -0.08
    é¬ĵ
    -0.08
    .sy
    -0.08
    ecom
    -0.08
    POSITIVE LOGITS
    å®īåħ¨æĢ§
    0.10
    å£ħ
    0.10
    çĥĤ
    0.10
    å¿«æĬ¥
    0.09
    çķĻä½ı
    0.09
    论è¯ģ
    0.09
    çĸĨ
    0.09
     Approval
    0.09
    è¯ŀ
    0.09
    ç¼ł
    0.09
    Activations Density 0.084%

    No Known Activations