© 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. 7596
    Prev
    Next
    INDEX
    Explanations

    shoulder and knee 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
    Not in Any Lists

    No Comments

    Negative Logits
    ç®Ģ便
    -0.11
    ery
    -0.10
    åħ´èµ·
    -0.09
    è¾ĥ好
    -0.09
    åĤij
    -0.09
    çĶ¨åľ°
    -0.09
    åºĹéĿ¢
    -0.09
    ëĭī
    -0.09
    åºķçĽĺ
    -0.09
    æ¢Ĺ
    -0.09
    POSITIVE LOGITS
    åľŁè±ª
    0.10
    ãģĵãģ¨ãģ§ãģĻ
    0.09
    æĺİå¹´
    0.09
    OME
    0.08
    åĪĿäºĮ
    0.07
    ../
    0.07
    TOT
    0.07
    æĸ¹éĿ¢
    0.07
    à¸ķา
    0.07
    åij¨åĽ´çļĦ
    0.07
    Activations Density 0.025%

    No Known Activations