© 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. 4861
    Prev
    Next
    INDEX
    Explanations

    continue or increase

    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
    éĤ£æŶ
    -0.09
    æĻĹ
    -0.09
    éĤ£æŶåĢĻ
    -0.09
    第ä¸Ģ次
    -0.09
    éĤ£ä¸ªæŶåĢĻ
    -0.09
    iers
    -0.08
    6
    -0.08
    éĺĶ
    -0.08
    æľ¦
    -0.08
    æŁIJç§įç¨ĭ度
    -0.08
    POSITIVE LOGITS
    è¿Ľä¸ĢæŃ¥
    0.16
    继ç»Ń
    0.15
     further
    0.15
    éĢ²ä¸ĢæŃ¥
    0.15
     далÑĮÑĪе
    0.14
     اÙĦÙħزÙĬد
    0.14
     weiter
    0.14
    è¦ģè¿Ľä¸ĢæŃ¥
    0.13
     далÑĮн
    0.13
    ç¹¼çºĮ
    0.13
    Activations Density 0.086%

    No Known Activations