© 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. 48862
    Prev
    Next
    INDEX
    Explanations

    Coca-Cola and coke products

    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
    .annot
    -0.09
    .mod
    -0.09
    ATTER
    -0.09
    èĪ°
    -0.09
    |=↵
    -0.08
    åĭĥåĭĥ
    -0.08
    çĶ¯
    -0.08
    è½´
    -0.08
    éĢĨè¢Ń
    -0.08
    quin
    -0.08
    POSITIVE LOGITS
    çĸ½
    0.10
    uco
    0.10
    æģĥ
    0.09
    翳
    0.09
     Boy
    0.08
    çĶŁäº§è½¦éĹ´
    0.08
    å¼ĢæľĹ
    0.08
    è¿Ļ份
    0.08
    å¾Ģäºĭ
    0.08
    åĬłæ·±
    0.08
    Activations Density 0.032%

    No Known Activations