© 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. 34355
    Prev
    Next
    INDEX
    Explanations

    airport security screening and search

    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
    çĨ¬å¤ľ
    -0.09
    æīĵäºĨ
    -0.09
     огÑĢаниÑĩен
    -0.09
    åŃ³
    -0.09
    转移åĪ°
    -0.08
    AndView
    -0.08
    Ùĩج
    -0.08
    tenant
    -0.08
    å¿į
    -0.08
    å°ıå¿ĥ
    -0.08
    POSITIVE LOGITS
    å®īæ£Ģ
    0.12
    éĢļè¡Į
    0.10
    è¿Ľåĩº
    0.10
    路人
    0.10
    åĩºå¢ĥ
    0.09
     passes
    0.09
    åĩºåħ¥å¢ĥ
    0.09
    éªĮ
    0.09
    éŸ
    0.09
    佩
    0.09
    Activations Density 0.142%

    No Known Activations