© 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. 32117
    Prev
    Next
    INDEX
    Explanations

    gravity

    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
     Prescott
    -0.10
    æĿµ
    -0.09
    å°º
    -0.09
    黾
    -0.09
    éĽĢ
    -0.09
    éĹªéĹª
    -0.09
    人群ä¸Ń
    -0.08
    /memory
    -0.08
    æĶ¹åĸĦ
    -0.08
    åĩ¶
    -0.08
    POSITIVE LOGITS
    å¼ķåĬĽ
    0.15
     gravity
    0.12
     Gravity
    0.11
    Gravity
    0.11
    .gravity
    0.11
     grav
    0.10
    ä¸Ģé¢Ĺ
    0.10
     attraction
    0.10
     gravitational
    0.10
    翻身
    0.10
    Activations Density 0.031%

    No Known Activations