© 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. 3864
    Prev
    Next
    INDEX
    Explanations

    professions and roles

    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
    ä½İ头
    -0.09
    acam
    -0.08
     pain
    -0.08
     anim
    -0.08
    dp
    -0.08
     Pain
    -0.08
    apist
    -0.08
    åīĤéĩı
    -0.08
    åĪ¶è£ģ
    -0.08
    ndon
    -0.08
    POSITIVE LOGITS
    æŶä¸į
    0.11
    å¤ļä¸ªåĽ½å®¶
    0.09
    åľ°çIJĥä¸Ĭ
    0.09
    /form
    0.09
    Brains
    0.09
    åľ¨ä»ĸçļĦ
    0.09
     ApplicationException
    0.09
    æľ¬äºº
    0.09
    åħ±åĴĮ
    0.08
     Viet
    0.08
    Activations Density 0.256%

    No Known Activations