© 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. 19859
    Prev
    Next
    INDEX
    Explanations

    deputy chief manager minister public official

    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
    éĩįçĤ¹é¢ĨåŁŁ
    -0.09
    irable
    -0.09
    isten
    -0.09
    éºĤ
    -0.09
    ç¥Ģ
    -0.09
    åŃ©åŃIJçļĦ
    -0.09
    çĥľ
    -0.09
    éŨå¤ĸ
    -0.08
    åŁİåł¡
    -0.08
    å¾ģ
    -0.08
    POSITIVE LOGITS
    ByteBuffer
    0.09
    åĬ©
    0.09
     Chief
    0.09
    éĩįå¿ĥ
    0.08
     youngest
    0.08
    èĩ¾
    0.08
     chief
    0.08
    ç²¾
    0.08
    å®£ä¼ł
    0.08
     Giants
    0.07
    Activations Density 0.038%

    No Known Activations