© 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. 24296
    Prev
    Next
    INDEX
    Explanations

    use and how

    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
    пÑĢеÑģÑģ
    -0.10
    è¿ģ
    -0.10
    è·»
    -0.08
    ä¸Ĭåįĩ
    -0.08
    çªĸ
    -0.08
    èĿ
    -0.08
    æīĢåľ¨çļĦ
    -0.08
     Supply
    -0.08
    ä¾Ľç»Ļ
    -0.08
     Shank
    -0.08
    POSITIVE LOGITS
    çĶ¨éĢĶ
    0.25
    æŃ£å¸¸ä½¿çĶ¨
    0.13
    uses
    0.12
    Uses
    0.12
     uses
    0.12
    åĪ©çĶ¨
    0.11
    å¤Ħç½®
    0.11
     misuse
    0.11
     íĻľìļ©
    0.11
     иÑģполÑĮзованиÑı
    0.11
    Activations Density 0.155%

    No Known Activations