© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 60675
    Prev
    Next
    INDEX
    Explanations

    malaria and its impacts

    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
    Negative Logits
    sert
    -0.09
    èĬ¸
    -0.09
    ród
    -0.09
    å¿¡
    -0.09
    主義
    -0.09
    å³Ħ
    -0.09
    ters
    -0.09
    ORIA
    -0.09
    inski
    -0.08
    NESS
    -0.08
    POSITIVE LOGITS
    à¹Į
    0.09
    kah
    0.09
    aud
    0.09
    è´¨éĩıéĹ®é¢ĺ
    0.09
    iv
    0.09
    hel
    0.09
    åĩłä½į
    0.08
    logged
    0.08
    äºĨ
    0.08
    0.08
    Activations Density 0.039%

    No Known Activations