© 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. 5550
    Prev
    Next
    INDEX
    Explanations

    renal failure 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
    IMIT
    -0.09
    ä¹ł
    -0.08
     Santo
    -0.08
    ië
    -0.08
    æķĻ室
    -0.08
     tav
    -0.08
    _widgets
    -0.08
    檩
    -0.08
     Sanct
    -0.08
    çľī
    -0.08
    POSITIVE LOGITS
    èĤ¾èĦı
    0.10
     neph
    0.09
    å·©
    0.09
    åºŁæ°´
    0.09
    æ°´éĩı
    0.09
    åłµå¡ŀ
    0.09
    æ°´èµĦæºIJ
    0.09
    èĽIJ
    0.09
    oda
    0.09
    çĽ¸äº²
    0.09
    Activations Density 0.505%

    No Known Activations