© 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. 19357
    Prev
    Next
    INDEX
    Explanations

    cafes

    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
     xấu
    -0.09
    æĹłçŁ¥
    -0.08
     Jr
    -0.08
    èµĸ以
    -0.08
    èĩªçĦ¶
    -0.08
    ONUS
    -0.08
    ted
    -0.08
    led
    -0.08
    ç©¿çĿĢ
    -0.08
     Smart
    -0.08
    POSITIVE LOGITS
    åĴĸåķ¡
    0.14
    coffee
    0.12
    èIJ¥ä¸ļ
    0.11
    âĺķ
    0.11
     coffee
    0.10
    èĮ¶åĽŃ
    0.09
     caffe
    0.09
    icode
    0.09
    èĮĹ
    0.09
     coff
    0.09
    Activations Density 0.011%

    No Known Activations