© 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. 2170
    Prev
    Next
    INDEX
    Explanations

    West Virginia, Swift, King, boot

    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
     HOLDER
    -0.10
    è°
    -0.09
    æ²¹èĦĤ
    -0.09
    æ·±åħ¥äºĨ解
    -0.09
    迹
    -0.09
    次è¦ģ
    -0.09
    åĮĹæŀģ
    -0.09
    订
    -0.08
    stick
    -0.08
    å·¥ä¸ļåĽŃåĮº
    -0.08
    POSITIVE LOGITS
    rek
    0.10
    Ñĥгл
    0.09
    åħĢ
    0.08
     Hyde
    0.08
    	Ext
    0.08
    LM
    0.08
    лей
    0.08
    æĻļæĬ¥
    0.08
    æľĢéĢĤåIJĪ
    0.08
    å»ĵ
    0.08
    Activations Density 0.002%

    No Known Activations