© 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. 31376
    Prev
    Next
    INDEX
    Explanations

    professions ending in "er"

    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
    èĪ¬
    -0.10
    -like
    -0.10
    èĪ¬çļĦ
    -0.09
    åıijå±ķä¸Ń
    -0.09
    æĬ¥åijĬæľŁåĨħ
    -0.09
    ä¼ŀ
    -0.09
    .lambda
    -0.09
    äºĮåŃĹ
    -0.09
    éĹ¹
    -0.09
    éĺŁä¼į建设
    -0.09
    POSITIVE LOGITS
    æѤåĪ»
    0.08
    ØŃÙĤ
    0.08
    arning
    0.08
     Arnold
    0.08
    anes
    0.08
    lus
    0.08
    dana
    0.08
    .confirm
    0.07
    榴
    0.07
    示èĮĥåĮº
    0.07
    Activations Density 0.180%

    No Known Activations