© 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. 27943
    Prev
    Next
    INDEX
    Explanations

    don't see how/any/where

    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
    éľ¹
    -0.09
    çľĭçľĭ
    -0.09
    pitch
    -0.09
    深深
    -0.09
    æĽ´å®¹æĺĵ
    -0.09
    èİŀ
    -0.08
    æľĢå°ij
    -0.08
    GINE
    -0.08
     пÑĢоÑģÑĤо
    -0.08
    åħ¸
    -0.08
    POSITIVE LOGITS
    æĢİä¹Īä¼ļ
    0.11
    æĭĽ
    0.10
    çģµæĦŁ
    0.09
    lbrace
    0.09
    éĶ´
    0.09
    å¿ħè¦ģ
    0.09
    åı¬
    0.08
    è¿ĺæĺ¯ä¼ļ
    0.08
    çĥŃæ½®
    0.08
    å®ŀè´¨
    0.08
    Activations Density 0.023%

    No Known Activations