© 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. 4550
    Prev
    Next
    INDEX
    Explanations

    Lily or variations followed by names/places

    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
    ä¸ĩæĪ·
    -0.10
    leon
    -0.09
    æŀ¢çº½
    -0.09
    edList
    -0.09
    ÙĦÙħ
    -0.08
    sWith
    -0.08
    ìĤ¬ë¬´
    -0.08
    /edit
    -0.08
    CTOR
    -0.08
    éķ¿éĢĶ
    -0.08
    POSITIVE LOGITS
    å¨ĺ
    0.10
    aneously
    0.10
    crate
    0.09
     geçen
    0.09
    opsy
    0.08
    å©¿
    0.08
    éļ¼
    0.08
     ÑģебÑı
    0.08
    hard
    0.08
    verts
    0.08
    Activations Density 0.005%

    No Known Activations