© 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. 22886
    Prev
    Next
    INDEX
    Explanations

    need to create something

    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
    俨
    -0.10
    æĬij
    -0.10
     полÑĥ
    -0.08
    çļĦä¸Ģ大
    -0.08
    仪
    -0.08
    éĶ²
    -0.08
    æĹłä¸į
    -0.08
    åĩij
    -0.08
    ickle
    -0.07
    æĸ¹æīį
    -0.07
    POSITIVE LOGITS
    åģıåIJij
    0.10
    ificate
    0.10
    强æĤį
    0.09
    åĴĮåħ¶ä»ĸ
    0.09
    大约
    0.09
    éĤ£æł·çļĦ
    0.09
    ä¹Łä¸įæĥ³
    0.08
    羣æŃ£çļĦ
    0.08
    为äºĨæĽ´å¥½
    0.08
     поÑĩÑĤи
    0.08
    Activations Density 2.425%

    No Known Activations