© 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. 54683
    Prev
    Next
    INDEX
    Explanations

    gaze, eye contact, straight ahead, squarely, direction

    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
    å¾Ĵ
    -0.08
    åĪĨåĮĸ
    -0.08
     outer
    -0.08
    éĻIJ
    -0.08
    uiten
    -0.08
     acted
    -0.08
     Dixon
    -0.08
    alen
    -0.07
     UI
    -0.07
     co
    -0.07
    POSITIVE LOGITS
    çļĦ缮åħī
    0.15
     gaze
    0.13
     stare
    0.13
    çļĦçľ¼ç¥ŀ
    0.12
    缮åħī
    0.12
    çľ¼çIJĥ
    0.12
     зÑĢ
    0.12
    çľ¼ç¥ŀ
    0.11
    çļĦçľ¼åħī
    0.11
    æŃ£å¸¸ä½¿çĶ¨
    0.11
    Activations Density 0.050%

    No Known Activations