© 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. 19750
    Prev
    Next
    INDEX
    Explanations

    Actually, certainly, basically

    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
    åħ¬å¼Ģåıij
    -0.11
    éĽĨåĽ¢èĤ¡ä»½
    -0.10
    级åĪ«çļĦ
    -0.10
    æľĢ好æĺ¯
    -0.09
    åħ¶æ¬¡æĺ¯
    -0.09
    å®ŀåľ¨æĺ¯å¤ª
    -0.09
    äºĨ好åĩł
    -0.09
    çĤ½
    -0.09
    æĺ¯çľŁçļĦ
    -0.09
    ä¹ħäºĨ
    -0.09
    POSITIVE LOGITS
    æѧè§Ĩ
    0.09
    eln
    0.09
    åħ¨éĥ¨
    0.08
     Disclaimer
    0.08
     senses
    0.08
    quat
    0.08
    nal
    0.08
    ngr
    0.08
    KW
    0.08
    ç³ģ
    0.08
    Activations Density 0.297%

    No Known Activations