© 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. 63657
    Prev
    Next
    INDEX
    Explanations

    root for

    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
    inke
    -0.10
    inia
    -0.10
    æī§æĶ¿
    -0.10
    å¼Ģåĩº
    -0.09
    主线
    -0.09
    ç»Łæ²»
    -0.09
     pockets
    -0.09
    åĩºæīĭ
    -0.09
    路人
    -0.08
    åįĸæİī
    -0.08
    POSITIVE LOGITS
    çłĶ究人åijĺ
    0.09
    åıįåĩ»
    0.08
    -days
    0.08
    	read
    0.08
    ãģ¤
    0.08
    uml
    0.08
    inspect
    0.08
    åIJĪæł¼
    0.08
    ä¸Ńå°ı
    0.07
    èĢģèĻİ
    0.07
    Activations Density 0.002%

    No Known Activations