© 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. 1920
    Prev
    Next
    INDEX
    Explanations

    stenosis or obstruction

    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
    åŃ©
    -0.11
    说çļĦè¯Ŀ
    -0.09
     fir
    -0.09
    åģĥ
    -0.09
    å¦ĤæѤ
    -0.08
    ews
    -0.08
    对èĩªå·±çļĦ
    -0.08
    è¸ıåħ¥
    -0.08
    çģµæķı
    -0.08
    åIJİæĤĶ
    -0.08
    POSITIVE LOGITS
    ลà¸Ńย
    0.10
    éļľç¢į
    0.09
    ä¸ĢéĶ®
    0.09
    ãĥĵãĥ«
    0.09
     hamm
    0.09
    bars
    0.08
     Rosenstein
    0.08
     constr
    0.08
    _enum
    0.08
    æĸ©
    0.08
    Activations Density 0.352%

    No Known Activations