© 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. 50250
    Prev
    Next
    INDEX
    Explanations

    talks and negotiations

    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
    ä¸ĥæĺŁ
    -0.09
    é¢ł
    -0.09
    æ·ĭ
    -0.09
    ÚĮ
    -0.09
    ä¼łæĴŃ
    -0.08
    è¡Į使
    -0.08
    广大群ä¼Ĺ
    -0.08
    éĥ
    -0.08
     Shower
    -0.08
    票
    -0.08
    POSITIVE LOGITS
    è°ĪåĪ¤
    0.23
     negotiations
    0.17
    ç£ĭåķĨ
    0.16
    æ´½è°Ī
    0.16
     talks
    0.16
    ä¼ļè°Ī
    0.16
    è°Ī
    0.16
    è«ĩ
    0.15
    对è¯Ŀ
    0.15
     negotiation
    0.15
    Activations Density 0.066%

    No Known Activations