© 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. 954
    Prev
    Next
    INDEX
    Explanations

    HIV disease and patients

    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
    MDB
    -0.09
    ä¿®åħ»
    -0.09
    Detach
    -0.09
    ãĥļãĥĥãĥĪ
    -0.08
    亲åŃIJ
    -0.08
     vot
    -0.08
    èĪįå¾Ĺ
    -0.08
    å¾Ģå¤ĸ
    -0.08
     parachute
    -0.08
    æݸ
    -0.08
    POSITIVE LOGITS
     AIDS
    0.16
    èī¾æ»ĭçĹħ
    0.15
     HIV
    0.14
    èī¾æ»ĭ
    0.14
    /AIDS
    0.11
    åįĹéĿŀ
    0.10
    æıIJ款
    0.10
    æµĨ
    0.10
    çĸ
    0.09
    æĦŁæŁĵèĢħ
    0.09
    Activations Density 0.259%

    No Known Activations