© 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. 1332
    Prev
    Next
    INDEX
    Explanations

    intracerebrally, intravenously, intraluminal

    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
     sẵn
    -0.09
     tÃłn
    -0.09
    æ¥ŀ
    -0.09
    isque
    -0.09
    IJ
    -0.08
    alue
    -0.08
    åĽ°
    -0.08
     pog
    -0.08
    è¦ģåģļ
    -0.08
     sque
    -0.08
    POSITIVE LOGITS
    лÑı
    0.11
    icom
    0.10
    ottie
    0.10
    .inject
    0.09
    edList
    0.09
     injections
    0.09
    çķ¿
    0.09
     пÑĢог
    0.09
    æĸ°çļĦä¸Ģ
    0.09
    ä¸įåIJĮç±»åŀĭ
    0.09
    Activations Density 0.332%

    No Known Activations