© 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. 24224
    Prev
    Next
    INDEX
    Explanations

    insurance

    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
    ä¸į说
    -0.10
    æ¿ł
    -0.09
    åŁ¸
    -0.09
    âĸ¾
    -0.09
    çĩĶ
    -0.09
    è°²
    -0.09
    è¿Ĥ
    -0.09
    çĶ©
    -0.09
    æķ£åıij
    -0.09
    强èĢħ
    -0.08
    POSITIVE LOGITS
    ä¿ĿéĻ©
    0.14
    ä¿Ŀéļª
    0.11
     insurance
    0.11
     Insurance
    0.10
    BST
    0.09
    è¦ĨçĽĸ
    0.09
    ç»Ļèĩªå·±
    0.09
     vent
    0.09
    Insurance
    0.09
    insurance
    0.08
    Activations Density 0.034%

    No Known Activations