© 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. 63388
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    è½»
    -0.09
    ç»į
    -0.09
    è¼ķ
    -0.09
    æ»ı
    -0.08
    èģĮ称
    -0.08
    ä¸ĵ
    -0.08
    lovak
    -0.08
    ä½ĵè´´
    -0.08
    åį¡æĭī
    -0.08
    asc
    -0.08
    POSITIVE LOGITS
    å¤ļæł·æĢ§
    0.21
     diversity
    0.17
     Diversity
    0.17
    å¤ļæł·
    0.16
    å¤ļæł·åĮĸ
    0.14
    å¤ļåħĥåĮĸ
    0.14
    å¤ļåħĥ
    0.13
     ëĭ¤ìĸij
    0.13
     diverse
    0.12
    å·®å¼Ĥ
    0.11
    Activations Density 0.071%

    No Known Activations