© 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. 47760
    Prev
    Next
    INDEX
    Explanations

    exposure to toxins and cancer

    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
     ÑĢол
    -0.10
    å°§
    -0.09
    æĮģ
    -0.09
    ç»ıè´¸
    -0.09
    大使
    -0.08
    纵
    -0.08
    æĭ¯
    -0.08
     Edwin
    -0.08
     glory
    -0.08
    çĸı
    -0.08
    POSITIVE LOGITS
    æİĴæ¯Ĵ
    0.12
    人å±ħ
    0.11
    æ¯Ĵ
    0.11
    ä¸Ńæ¯Ĵ
    0.10
    eses
    0.10
     ngá»Ļ
    0.09
    çĩĥçħ¤
    0.09
    DCF
    0.09
    èĩ´çĻĮ
    0.09
    åıĹåĪ°å½±åĵį
    0.09
    Activations Density 0.750%

    No Known Activations