© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38683
    Prev
    Next
    INDEX
    Explanations

    ozone layer

    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
    Ghost
    -0.10
    æݧ
    -0.09
    äºĶå®ĺ
    -0.09
    平淡
    -0.09
    èĽ©
    -0.09
    éĩĩéĽĨ
    -0.08
    管æݧ
    -0.08
     Ghost
    -0.08
    æĬ¼
    -0.08
    éĤ¯
    -0.08
    POSITIVE LOGITS
    ç´«å¤ĸ线
    0.11
    ä¸ĢåŃĹ
    0.10
    çŀ©
    0.10
    说å®ŀ
    0.10
    æ§İ
    0.09
    æķıæĦŁ
    0.08
    èĩŃ
    0.08
    åŃĶéĽĢ
    0.08
    ä¹ĭæĺŁ
    0.08
    totals
    0.08
    Activations Density 0.016%

    No Known Activations