© 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. 50927
    Prev
    Next
    INDEX
    Explanations

    disk and disease

    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
     Gest
    -0.09
    iez
    -0.09
    çĨŁçŁ¥
    -0.08
    Ø·Ùħ
    -0.08
    å¾¼
    -0.08
     Alley
    -0.08
    éĴ¦
    -0.08
    elsey
    -0.08
    æİĴéĺŁ
    -0.08
    éĽĨ
    -0.08
    POSITIVE LOGITS
     Sandwich
    0.10
    é«Į
    0.09
    ç«Ļéķ¿
    0.09
    ç»ĪçĶŁ
    0.09
    å¥Ĺ
    0.09
    年人
    0.09
    _CHK
    0.09
    年轻人
    0.09
    翳
    0.09
    åī©ä¸ĭ
    0.09
    Activations Density 0.161%

    No Known Activations