© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20009
    Prev
    Next
    INDEX
    Explanations

    order processing

    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
     Bradley
    -0.09
    OLE
    -0.09
    çŁ³æ²¹åĮĸå·¥
    -0.09
    éĹ°
    -0.08
    hower
    -0.08
    xes
    -0.08
    éĶ¶
    -0.08
     Ãĸl
    -0.08
    craft
    -0.08
    igel
    -0.08
    POSITIVE LOGITS
    订åįķ
    0.17
     orders
    0.12
    éĤij
    0.11
    è¨Ĥ
    0.11
    orders
    0.11
    订
    0.11
    .orders
    0.11
    ä¸ĭåįķ
    0.10
    çĿ£åĬŀ
    0.10
     order
    0.10
    Activations Density 0.061%

    No Known Activations