© 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. 47905
    Prev
    Next
    INDEX
    Explanations

    found to be

    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
    æĥľ
    -0.12
    å¹²äºĭ
    -0.11
    uttle
    -0.11
     chance
    -0.10
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    ç§Ń
    -0.09
    åĿĽ
    -0.09
    tit
    -0.08
    ç§ī
    -0.08
    éĩijåŃĹ
    -0.08
    POSITIVE LOGITS
    oire
    0.10
    AKER
    0.09
    åµĮ
    0.09
    使人
    0.09
    æĢ¥
    0.09
    ç½®
    0.09
    yn
    0.09
    bern
    0.08
    ç¼ļ
    0.08
     Briggs
    0.08
    Activations Density 0.066%

    No Known Activations