© 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. 27794
    Prev
    Next
    INDEX
    Explanations

    learn more about

    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
    æĽ´å¤ļ
    -0.11
    樾
    -0.11
    æĽ´å¤ļçļĦæĺ¯
    -0.10
    åħµåĻ¨
    -0.09
     enough
    -0.09
    æľīå¾Īå¤ļç§į
    -0.09
    ä»Ģä¹Īä¸ľè¥¿
    -0.09
    åıĪæľī
    -0.09
    æĢĽ
    -0.09
    THR
    -0.08
    POSITIVE LOGITS
    æĬĢæľ¯åĴĮ
    0.10
    -than
    0.09
    usc
    0.09
    cape
    0.09
    æľ¬æĬ¥
    0.09
    åĽ°æī°
    0.09
    åıijæĮ¥äºĨ
    0.09
    æµģåIJij
    0.08
    è¯Ģ
    0.08
    abouts
    0.08
    Activations Density 0.023%

    No Known Activations