© 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. 30131
    Prev
    Next
    INDEX
    Explanations

    food and drink

    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¸Ļ
    -0.09
    жив
    -0.09
    ocker
    -0.08
    æī¿
    -0.08
     bottleneck
    -0.08
    spr
    -0.08
    vice
    -0.08
    çģĮ
    -0.08
    oke
    -0.08
    è¿·
    -0.08
    POSITIVE LOGITS
    èħ¥
    0.10
    fat
    0.10
    çIJ¬
    0.09
    åIJĮä¸Ģ个
    0.09
    éĥ½éĿŀ常
    0.09
     Pell
    0.08
    岸
    0.08
    å¼ĢåıijåĪ©çĶ¨
    0.08
    عا
    0.08
     feas
    0.08
    Activations Density 0.181%

    No Known Activations