© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7619
    Prev
    Next
    INDEX
    Explanations

    diabetes mellitus

    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
    æħ·æħ¨
    -0.10
    3
    -0.08
    æ¶Įçİ°åĩº
    -0.08
    笼
    -0.08
    1
    -0.08
     Hayes
    -0.07
    èĽ®
    -0.07
    Accessor
    -0.07
    9
    -0.07
    5
    -0.07
    POSITIVE LOGITS
    è¡Ģç³ĸ
    0.12
    ç³ĸå°¿
    0.12
    è´¡
    0.11
    èĥ°
    0.10
    æī¶è´«å·¥ä½ľ
    0.10
    è´«åĽ°äººåı£
    0.10
     insulin
    0.10
    ç³ĸå°¿çĹħ
    0.10
    ImageContext
    0.10
    é¤IJ
    0.10
    Activations Density 0.442%

    No Known Activations