© 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. 33585
    Prev
    Next
    INDEX
    Explanations

    cash registers and cashier sales

    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
    åĨī
    -0.11
    å¸Ń
    -0.11
    æĭľè®¿
    -0.10
    Sher
    -0.09
    çĥ½
    -0.09
    转åĮĸ为
    -0.09
     ÑĥÑĩаÑģÑĤник
    -0.09
    èĻ±
    -0.09
    æݨåĩºçļĦ
    -0.09
    大声
    -0.09
    POSITIVE LOGITS
    æ¢
    0.09
    9
    0.09
    psc
    0.08
    碣
    0.08
    5
    0.08
    åŃIJåŃĻ
    0.08
     granddaughter
    0.08
    帮
    0.08
    åĪĨè¡Į
    0.08
    å¾Ĺ天
    0.08
    Activations Density 0.070%

    No Known Activations