© 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. 54085
    Prev
    Next
    INDEX
    Explanations

    autoimmune diseases

    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
    åĻİ
    -0.10
     Wonderful
    -0.09
     @$_
    -0.09
    æĨĭ
    -0.09
    éħįåIJĪ
    -0.09
    æĶĿ
    -0.09
    ATAL
    -0.09
    æijĦ
    -0.09
    åĿł
    -0.09
    åĪ«å¢ħ
    -0.09
    POSITIVE LOGITS
    åĽ´
    0.10
    æ¼ı
    0.09
    KA
    0.09
     Chess
    0.09
    鹿
    0.09
    æĶ»
    0.09
    éĿ¶
    0.08
    æĢ§çĸ¾çĹħ
    0.08
     polar
    0.08
    åŀĵ
    0.08
    Activations Density 0.295%

    No Known Activations