© 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. 30715
    Prev
    Next
    INDEX
    Explanations

    Trump payment scandals

    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
    ä¾ł
    -0.13
    åĽĽæĸ¹
    -0.09
    è¿ĺå¾Ĺ
    -0.09
    rary
    -0.09
    èĭ¦
    -0.09
    ä¸Ģ线
    -0.09
     indef
    -0.08
    éªĪ
    -0.08
    iron
    -0.08
     promises
    -0.08
    POSITIVE LOGITS
     impeachment
    0.14
     impe
    0.11
    æ¸İ
    0.10
    诽
    0.10
    å§ĭç»Īä¿ĿæĮģ
    0.10
    داÙĨ
    0.10
    ä¸įèĩ³äºİ
    0.09
    åĬ¾
    0.09
    常å§Ķ
    0.09
    ç³ľ
    0.09
    Activations Density 0.057%

    No Known Activations