© 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. 26639
    Prev
    Next
    INDEX
    Explanations

    used aseasy to understandsought after resourcein your pocketsuccessful for the pressworked through themselvesneeded for process controltried to go theregood to understand

    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
    å¾ģéĽĨ
    -0.09
    æľī趣çļĦ
    -0.09
    ç½ijåıĭè¯Ħ论
    -0.08
    ÑģилÑĮ
    -0.08
    è¿Ļä¸Ģå¹´
    -0.08
    è¿Ļ个è¯į
    -0.08
    å¼±åĬ¿
    -0.08
    åݲ
    -0.08
    å°ıé¢Ŀ
    -0.08
    è¿Ļä¸ĢåĪ»
    -0.08
    POSITIVE LOGITS
    éĺħè§Ī
    0.12
    éĺħ读
    0.11
    åį°åĪ·
    0.11
    æĶ¶èĹı
    0.11
    ä¸Ģæľ¬
    0.11
    纸质
    0.10
    å®ŀçĶ¨æĢ§
    0.10
    æŁ¥éĺħ
    0.10
     Bookmark
    0.10
     handy
    0.09
    Activations Density 0.123%

    No Known Activations