© 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. 34456
    Prev
    Next
    INDEX
    Explanations

    kidney damage, disease, transplantation

    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
    æµĶ
    -0.10
    s
    -0.10
    naments
    -0.09
    opher
    -0.09
    ities
    -0.09
    inda
    -0.09
    own
    -0.09
    onical
    -0.09
    ãĤ¤ãĥ«
    -0.09
    idable
    -0.08
    POSITIVE LOGITS
    ãģĬãģı
    0.09
    stag
    0.09
    roker
    0.09
     Preconditions
    0.08
    emia
    0.08
    ç»ĿæľĽ
    0.08
     Ung
    0.08
    讵
    0.08
    ä¼
    0.08
    quir
    0.07
    Activations Density 0.026%

    No Known Activations