© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37890
    Prev
    Next
    INDEX
    Explanations

    risk of developing or experiencing conditions

    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
     Mature
    -0.11
    olen
    -0.09
    åħ´å¥ĭ
    -0.09
    ä¼ij
    -0.09
     erfol
    -0.09
    orman
    -0.09
    åľ¨äºİ
    -0.08
    诱人
    -0.08
    ivol
    -0.08
     Kills
    -0.08
    POSITIVE LOGITS
    è¿Ļè¾ĪåŃIJ
    0.12
    ç»Ī身
    0.12
    ä¸Ģè¾ĪåŃIJ
    0.11
    ç»ĪçĶŁ
    0.11
    ä»ĬçĶŁ
    0.11
    çļĦæ¦Ĥçİĩ
    0.09
    åŃIJåŃĻ
    0.09
    æĻļå¹´
    0.09
    åĩłåįģå¹´
    0.09
    å²ģæľĪ
    0.09
    Activations Density 0.249%

    No Known Activations