© 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. 62861
    Prev
    Next
    INDEX
    Explanations

    professional tennis tournament

    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
    å°Ħåĩ»
    -0.09
     Bav
    -0.09
    _LVL
    -0.09
    éĢĢè¿ĺ
    -0.09
    让æ¶Īè´¹èĢħ
    -0.09
    gress
    -0.09
    彩
    -0.09
    åŁºè¾ħ
    -0.09
    äºĮ次
    -0.08
    ãģĹãĤĥ
    -0.08
    POSITIVE LOGITS
    åĮĹæĸ¹
    0.11
    èĬĤ
    0.10
    æľīå¿ħè¦ģ
    0.09
    è±Ĩ
    0.09
    åīįæīĢæľªæľī
    0.09
    gfx
    0.09
    ä¸ļä½Ļ
    0.09
    umont
    0.09
    èĩªå¾ĭ
    0.08
    éĻĦå±ŀ
    0.08
    Activations Density 0.094%

    No Known Activations