© 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. 10565
    Prev
    Next
    INDEX
    Explanations

    super bowl or final game

    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
    åģĮ
    -0.09
    æĹłç¼ĺ
    -0.09
    åľ°ä¸Ń
    -0.08
    满满
    -0.08
    è£ģåijĺ
    -0.08
    强åĬ²
    -0.08
    ãĤıãĤĬ
    -0.08
    UA
    -0.08
    åħįéĻ¤
    -0.08
    chai
    -0.08
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.11
    楹
    0.10
    åIJ¬çĿĢ
    0.10
    å¢ħ
    0.09
    ä¸įçĽ¸ä¿¡
    0.09
    éļĨ
    0.09
    çĴ©
    0.09
     StringUtil
    0.09
    ä¸ĸçķĮè§Ĥ
    0.09
    åħ¨è¿ĩç¨ĭ
    0.09
    Activations Density 0.129%

    No Known Activations