© 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. 34567
    Prev
    Next
    INDEX
    Explanations

    cutting food ingredients

    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
    ÙĤا
    -0.09
    èĵĿåĽ¾
    -0.09
    walker
    -0.09
    æ³Ķ
    -0.09
    æľīçļĦ
    -0.09
    ourn
    -0.09
    åĮł
    -0.09
    æ¬ł
    -0.08
    rious
    -0.08
     hẹn
    -0.08
    POSITIVE LOGITS
    åı¦ä¸Ģä½į
    0.09
    èĥª
    0.09
    缮æłĩ
    0.08
    çļĦ缮æłĩ
    0.08
    illed
    0.08
    çļĦ身影
    0.08
    vv
    0.08
    æĪı
    0.08
    ä¸ĢçĤ¹åĦ¿
    0.08
    åĩºåĩ»
    0.08
    Activations Density 0.006%

    No Known Activations