© 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. 34146
    Prev
    Next
    INDEX
    Explanations

    Airbus and aircraft

    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
    _RST
    -0.11
    离å¼ĢäºĨ
    -0.10
    æĴ¸
    -0.09
    à¹ģà¸Īà¸ģ
    -0.09
    åĨĽå·¥
    -0.09
    	RTE
    -0.09
    èIJ½åħ¥
    -0.09
    arine
    -0.09
    å¤ĸåľ°
    -0.09
    몰
    -0.09
    POSITIVE LOGITS
    æľºåŀĭ
    0.11
    çıŃ
    0.09
    容
    0.09
    æľºç»Ħ
    0.08
    忧èĻij
    0.08
    åĮºéĹ´
    0.08
    urat
    0.08
    ç»Ń
    0.08
    ä¹ħ
    0.08
    larg
    0.08
    Activations Density 0.196%

    No Known Activations