© 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. 7283
    Prev
    Next
    INDEX
    Explanations

    American Airlines ticket office

    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
    帽
    -0.11
    ä¸įå¤ļ
    -0.09
    enville
    -0.09
    ä¹ĥ
    -0.09
    äº
    -0.09
    зд
    -0.08
    à¸į
    -0.08
    äºĭ项
    -0.08
    æ´ĹåĩĢ
    -0.08
    å¸Ĥä¸Ńå¿ĥ
    -0.08
    POSITIVE LOGITS
    客æĪ·æľįåĬ¡
    0.10
    cone
    0.10
    iales
    0.10
    æµģæ°´
    0.09
    æĢ»çIJĨ
    0.09
    ç¬ij声
    0.09
    çIJĨèµĶ
    0.09
    åķ¸
    0.09
    cascade
    0.09
    å°±ä¸ļå²Ĺä½į
    0.09
    Activations Density 0.070%

    No Known Activations