© 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. 5933
    Prev
    Next
    INDEX
    Explanations

    body parts and medical conditions

    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
    åľ°çIJĥä¸Ĭ
    -0.11
    åĪ©äºļ
    -0.10
    åĸī
    -0.10
    iew
    -0.09
    æĮijåīĶ
    -0.09
    ita
    -0.09
    ç´¢åıĸ
    -0.09
    ä¼IJ
    -0.09
    å½¼æѤ
    -0.09
    们
    -0.09
    POSITIVE LOGITS
    åĨħçļĦ
    0.10
    æ·±å¤Ħ
    0.10
    é£Ĵ
    0.09
    éĩĮçļĦ
    0.09
    éĥ¨åī¯
    0.09
    æ´»åĬ¨ä¸Ń
    0.08
    lover
    0.08
     spells
    0.08
     Avery
    0.08
    ategy
    0.08
    Activations Density 0.443%

    No Known Activations