© 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. 39063
    Prev
    Next
    INDEX
    Explanations

    pertussis, tetanus, immunization

    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
    gio
    -0.09
    è¿ĩæĿ¥
    -0.08
     Rut
    -0.08
    .partial
    -0.08
     Chamber
    -0.08
    æľį
    -0.08
    çĶŁçIJĨ
    -0.08
    æ´»
    -0.08
    entina
    -0.08
    大éħĴåºĹ
    -0.08
    POSITIVE LOGITS
    åĪ®
    0.10
    æ¥ł
    0.09
    è´¤
    0.09
    æľªå©ļ
    0.09
    ains
    0.08
    çļĦåŃĺåľ¨
    0.08
    åIJįå¸Ī
    0.08
    å¦ŀ
    0.08
    åĩºè·¯
    0.08
     Passed
    0.08
    Activations Density 0.061%

    No Known Activations