© 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. 19105
    Prev
    Next
    INDEX
    Explanations

    and or

    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
    æŶéĹ´åĴĮ
    -0.09
    失误
    -0.09
    ä¼ģä¸ļåĴĮ
    -0.09
    -vs
    -0.09
    æĮĤ
    -0.09
    ç¥ī
    -0.09
    ä½ıäºĨ
    -0.09
    èĭ¥å¹²
    -0.09
    å¼ķæĿ¥
    -0.08
    à¤
    -0.08
    POSITIVE LOGITS
     \`
    0.09
    æĪĸèĢħ说
    0.09
    phans
    0.09
    una
    0.09
    ared
    0.08
    obia
    0.08
    彪
    0.08
    _DL
    0.08
     fur
    0.08
    .inst
    0.08
    Activations Density 0.206%

    No Known Activations