© 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. 38198
    Prev
    Next
    INDEX
    Explanations

    international law terms

    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
    åıªè¦ģæľī
    -0.09
    æ·ĸ
    -0.09
    ä¸Ģé¢Ĺ
    -0.09
    że
    -0.09
    ä¸į失
    -0.09
    综åIJĪç´łè´¨
    -0.09
    Äķ
    -0.09
    第ä¸ī代
    -0.08
    积æŀģéħįåIJĪ
    -0.08
    æĬĺèħ¾
    -0.08
    POSITIVE LOGITS
    åĽ½éĻħ
    0.10
    åıĮè¾¹
    0.09
     international
    0.09
    çĬ¯è§Ħ
    0.09
    enha
    0.08
    åĴĮå¹³
    0.08
    çĶŁçĶŁ
    0.08
    æĥ¯ä¾ĭ
    0.08
    æĿ¡çº¦
    0.08
    æĪIJè¯Ń
    0.08
    Activations Density 0.038%

    No Known Activations