© 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. 5687
    Prev
    Next
    INDEX
    Explanations

    sports teams and celiac disease

    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
    oleon
    -0.09
    ability
    -0.09
    å®ļäºĨ
    -0.09
    ricular
    -0.08
    olem
    -0.08
    iliar
    -0.08
    SOLE
    -0.08
    /comment
    -0.08
    lot
    -0.07
    ç§ĭåĨ¬
    -0.07
    POSITIVE LOGITS
    roma
    0.10
    åĽ¢è´Ń
    0.09
    DL
    0.09
    tics
    0.09
     ÙħÙĪضÙĪع
    0.09
    çĪ·
    0.09
    ç¬ı
    0.08
     Sandwich
    0.08
    çĮ¾
    0.08
    ا
    0.08
    Activations Density 0.006%

    No Known Activations