© 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. 63079
    Prev
    Next
    INDEX
    Explanations

    Bauhaus, module, mbox, Jam

    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
    å¤ļæł·åĮĸ
    -0.09
    éĶļ
    -0.09
     rack
    -0.09
    urry
    -0.08
    holm
    -0.08
    æĮĩçĿĢ
    -0.08
    å¤ļ彩
    -0.08
    åħĪè¡Į
    -0.08
    elon
    -0.08
    å¨ĺ
    -0.08
    POSITIVE LOGITS
    æĿ¥ä¸įåıĬ
    0.10
    ilter
    0.09
    满满çļĦ
    0.09
    éĻIJ度
    0.09
    è¾İ
    0.08
    æ¼Ĥ
    0.08
    çłº
    0.08
    DRV
    0.08
    unes
    0.08
    has
    0.08
    Activations Density 0.001%

    No Known Activations