© 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. 30619
    Prev
    Next
    INDEX
    Explanations

    metal, modern, python, citrus

    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
    -cross
    -0.09
    vest
    -0.09
    æľ¬å¸Ĥ
    -0.08
    ãģ¨ãģ¯ãģĦãģĪ
    -0.08
     verk
    -0.08
    æĢ
    -0.08
    ivate
    -0.08
    æªĢ
    -0.08
    åIJĵå¾Ĺ
    -0.08
     оÑģÑĥÑīеÑģÑĤв
    -0.08
    POSITIVE LOGITS
    ä¼¼çļĦ
    0.12
    çļĦæ°Ķæģ¯
    0.12
    èĪ¬çļĦ
    0.12
    æĦŁ
    0.12
    æ°Ķæģ¯
    0.12
    çļĦæĦŁè§ī
    0.11
    æľīä¸Ģç§į
    0.10
     ëĬIJëĤĮ
    0.10
    ä¼¼
    0.10
    èĪ¬
    0.10
    Activations Density 0.037%

    No Known Activations