© 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. 39777
    Prev
    Next
    INDEX
    Explanations

    poses, photo, cameras, selfies, blog

    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
    宣
    -0.10
    ãĤ¢ãĥĬ
    -0.10
    人ãģ¨
    -0.09
     phê
    -0.09
    æĬĬèĩªå·±çļĦ
    -0.09
    éļĶçĿĢ
    -0.09
    igits
    -0.08
    缸è§ģ
    -0.08
    peak
    -0.08
     tụ
    -0.08
    POSITIVE LOGITS
    ForRow
    0.10
    åĽºåĮĸ
    0.09
    poses
    0.09
    ruc
    0.09
     pose
    0.08
    çIJ°
    0.08
    åĬ¨åĬĽ
    0.08
    (Pos
    0.08
     Pos
    0.08
    æŀ¶
    0.08
    Activations Density 0.009%

    No Known Activations