© 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. 22944
    Prev
    Next
    INDEX
    Explanations

    vigilance or benefit

    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
    é¦ħ
    -0.09
    ä¾ı
    -0.08
    åĨįå¤ļ
    -0.08
    éĿ¢ä¸Ĭ
    -0.08
    å¼Ģ头
    -0.08
    æĬķåħ¥åĪ°
    -0.08
    åĭĻ
    -0.08
    Ъ
    -0.08
     Camping
    -0.08
    hardt
    -0.08
    POSITIVE LOGITS
    	TokenName
    0.10
    lamp
    0.10
    umn
    0.09
    éģĵ士
    0.09
    anter
    0.09
    à¸Ĥà¸Ńà¸ļ
    0.09
    ncia
    0.09
    rail
    0.09
    fur
    0.09
    工夫
    0.09
    Activations Density 0.005%

    No Known Activations