© 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. 32263
    Prev
    Next
    INDEX
    Explanations

    science explanations and theories

    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
    ç»ĩ
    -0.10
    ษ
    -0.09
    èĥĮ
    -0.09
    IAS
    -0.09
    æĬķæĶ¾
    -0.09
    å§IJ妹
    -0.09
    æĭ³
    -0.09
    fu
    -0.08
    æ·ĺ
    -0.08
    æĶ¶åī²
    -0.08
    POSITIVE LOGITS
    çı¥
    0.11
    å§ĭ建
    0.11
    ogui
    0.11
    æĹ©åľ¨
    0.10
    æ¿Ĥ
    0.10
    ä¹IJåĽŃ
    0.10
    ä¸ĢåĪĩ
    0.10
    à¹Ĥà¸ģ
    0.10
    çħĬ
    0.09
    åIJĪçIJĨæĢ§
    0.09
    Activations Density 0.193%

    No Known Activations