© 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. 49128
    Prev
    Next
    INDEX
    Explanations

    medical conditions and suffixes

    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
    们
    -0.10
    ãģ¤ãĤĤãĤĬ
    -0.10
    éĢļãĤĬ
    -0.09
    tern
    -0.09
    们çļĦ
    -0.09
    åģļèµ·
    -0.08
    ãģ¹ãģį
    -0.08
    ä¸įå¤Ł
    -0.08
    äºĭçī©
    -0.08
    ood
    -0.08
    POSITIVE LOGITS
     оÑĤд
    0.12
    åĢĻ
    0.10
     mell
    0.09
    OUS
    0.09
    å¾ĹåĪ°äºĨ
    0.09
    åĨµ
    0.09
    orphic
    0.09
     Mell
    0.09
    æĿĨèıĮ
    0.08
    åĹľ
    0.08
    Activations Density 0.836%

    No Known Activations