© 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. 26860
    Prev
    Next
    INDEX
    Explanations

    spotlight, focus, attention

    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
    æ²Ļæ¼ł
    -0.08
    леп
    -0.08
     dong
    -0.08
    panion
    -0.08
    лов
    -0.08
    odor
    -0.08
    欢åĸľ
    -0.08
     Flyers
    -0.08
    åłĨ
    -0.08
    éĤ£æł·çļĦ
    -0.08
    POSITIVE LOGITS
     spotlight
    0.23
    çĦ¦çĤ¹
    0.19
    èģļçĦ¦
    0.16
     Spotlight
    0.15
     attention
    0.14
     scrutiny
    0.14
    注æĦıåĬĽ
    0.13
     внимание
    0.13
    èĪŀåı°ä¸Ĭ
    0.12
    èģļ
    0.12
    Activations Density 0.098%

    No Known Activations