© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37867
    Prev
    Next
    INDEX
    Explanations

    lying, lied, lies, false

    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
    achable
    -0.08
     Tyson
    -0.08
     обÑĭ
    -0.08
    å¿ł
    -0.08
    ä¸ľè·¯
    -0.08
     <<<
    -0.08
    款项
    -0.08
    lez
    -0.07
    lein
    -0.07
    å«£
    -0.07
    POSITIVE LOGITS
    åĽŀé¦ĸ
    0.11
    ä¹łæĥ¯äºĨ
    0.09
    벨
    0.09
    fur
    0.09
    å·¥åİĤ
    0.09
    haar
    0.09
    ulence
    0.09
    æĪŁ
    0.09
     اÙĦÙĪا
    0.09
    äºĽä»Ģä¹Ī
    0.08
    Activations Density 0.017%

    No Known Activations