© 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. 57571
    Prev
    Next
    INDEX
    Explanations

    credit card and vendor credit

    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
    æĶ¶çº³
    -0.09
    æįį
    -0.09
    æĶ¶åĪ°
    -0.09
     caught
    -0.09
    æĶ¶åĪ°äºĨ
    -0.09
    æĽ¼
    -0.08
    ä¸ī人
    -0.08
    éŃģ
    -0.08
     jobs
    -0.08
     Globals
    -0.08
    POSITIVE LOGITS
    ä¿¡çĶ¨
    0.10
    é¢Ŀ度
    0.10
    èµĦ
    0.09
    วà¸ĩ
    0.09
    è¾ķ
    0.09
    å¤ĩçĶ¨
    0.09
    æİĪä¿¡
    0.09
    åij¼å£°
    0.08
    åºĹéĩĮ
    0.08
    åŁİéĩĮ
    0.08
    Activations Density 0.030%

    No Known Activations