© 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. 23279
    Prev
    Next
    INDEX
    Explanations

    courier delivery services

    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
    çĤ³
    -0.10
    æ®Ĭ
    -0.09
    çĹĽèĭ¦
    -0.09
     ÑĦинанÑģов
    -0.08
    fresh
    -0.08
    è¹ļ
    -0.08
    æ²Ĩ
    -0.08
    lesia
    -0.08
    å®īåħ¨çĶŁäº§
    -0.08
     обо
    -0.08
    POSITIVE LOGITS
    éĤ®æĶ¿
    0.10
    ãĤ³ãĥ¼
    0.10
    å¸ĥé²ģ
    0.09
     Postal
    0.09
    åĮħ裹
    0.09
    è¹
    0.09
    å¸ĥ
    0.09
     Stout
    0.09
    .sender
    0.09
     postal
    0.08
    Activations Density 0.081%

    No Known Activations