© 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. 40282
    Prev
    Next
    INDEX
    Explanations

    schistosomiasis, taenia solium

    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
    inski
    -0.09
    andle
    -0.09
    ishop
    -0.09
    æĻ¯
    -0.09
    insky
    -0.09
    -flash
    -0.09
     Hosp
    -0.09
    æı´
    -0.08
    gend
    -0.08
    çĩĥæĸĻçĶµæ±ł
    -0.08
    POSITIVE LOGITS
    èĻ±
    0.14
    èĻ«
    0.12
    èĽĶ
    0.11
    æĭĪ
    0.11
    æ¶ĪçģŃ
    0.10
     erad
    0.10
    娱
    0.10
    粪
    0.10
    acha
    0.09
    麻çĹ¹
    0.09
    Activations Density 0.330%

    No Known Activations