© 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. 27345
    Prev
    Next
    INDEX
    Explanations

    cooking and food preparation

    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
    é²ľ
    -0.10
    ç»¿åľ°
    -0.10
    æºIJæºIJ
    -0.09
    åIJİåı°
    -0.09
    roke
    -0.09
    èįīåĿª
    -0.09
    AAD
    -0.09
    åĤ§
    -0.09
    hel
    -0.09
    Sold
    -0.09
    POSITIVE LOGITS
    æĮº
    0.09
    æŀ«
    0.08
     Renault
    0.08
    bre
    0.08
    说æľį
    0.08
    两ä½į
    0.08
     bre
    0.08
    FER
    0.08
    anta
    0.08
    Fly
    0.08
    Activations Density 0.020%

    No Known Activations