© 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. 60563
    Prev
    Next
    INDEX
    Explanations

    fractures and injuries

    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
    ç¨į
    -0.11
    LER
    -0.10
    ä¹ĭäºī
    -0.09
     McInt
    -0.09
    ought
    -0.09
    å°ıç±³
    -0.09
    idity
    -0.09
    æĺ¾å¾Ĺ
    -0.09
    æķ°çłģ
    -0.08
    èĢ³è¾¹
    -0.08
    POSITIVE LOGITS
    骨头
    0.10
    亲身
    0.10
    åĿij
    0.10
    око
    0.08
    äºĭæķħåıijçĶŁ
    0.08
     scare
    0.08
    ated
    0.08
    èĬ±è´¹
    0.08
    èĪ¶
    0.08
     Tribal
    0.08
    Activations Density 0.022%

    No Known Activations