© 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. 21739
    Prev
    Next
    INDEX
    Explanations

    publishing and marketing industry

    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
    产
    -0.10
    æĴ°
    -0.10
    ä¸įå¼Ģ
    -0.10
    æĬ½åĩº
    -0.09
    åĨľçī§
    -0.09
    å¤ĸç§ij
    -0.09
    åıĹéĤĢ
    -0.09
    æĭĪ
    -0.09
    æ¬
    -0.09
    หย
    -0.09
    POSITIVE LOGITS
    èIJ¥éĶĢ
    0.11
    åıijè¡Į
    0.11
    躬
    0.09
    åģļ强
    0.09
    è¿IJèIJ¥
    0.09
    è¡¥
    0.09
     marketing
    0.09
    éŀł
    0.09
     Publisher
    0.09
     Publishers
    0.08
    Activations Density 0.111%

    No Known Activations