© 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. 38672
    Prev
    Next
    INDEX
    Explanations

    type 2 diabetes

    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
    _REDIRECT
    -0.10
    åŁĥ
    -0.09
    illis
    -0.09
    仪
    -0.09
    otte
    -0.08
    way
    -0.08
    otti
    -0.08
    çĹķ
    -0.08
    å¢ĥ
    -0.08
    ì
    -0.08
    POSITIVE LOGITS
    åĨľå®¶
    0.09
    aily
    0.09
    è§Ħ模æľĢ大
    0.09
    riers
    0.09
     pale
    0.09
    çij¢
    0.08
    ä»İ严
    0.08
     Peters
    0.08
    alendar
    0.08
    æĩĴ
    0.08
    Activations Density 0.200%

    No Known Activations