© 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. 50364
    Prev
    Next
    INDEX
    Explanations

    sports stats and gender identifiers

    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
    åħĥå®Ŀ
    -0.11
    çĤ¹äºĨ
    -0.09
     вообÑīе
    -0.09
    uai
    -0.09
    åħļçļĦé¢Ĩ导
    -0.09
    adel
    -0.09
    èij¶
    -0.08
    产åĵģè´¨éĩı
    -0.08
    alen
    -0.08
     Dü
    -0.08
    POSITIVE LOGITS
    å
    0.09
    çıī
    0.09
    è¿Ļ对
    0.08
    âĦł
    0.08
    oze
    0.08
    æ°¸ä¹ħ
    0.08
    æĪij对
    0.07
    ERA
    0.07
    REA
    0.07
    åħ¶ä¸Ńä¹ĭä¸Ģ
    0.07
    Activations Density 0.204%

    No Known Activations