© 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. 36035
    Prev
    Next
    INDEX
    Explanations

    flow of liquids and quantities

    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
    æ·±å±Ĥ
    -0.09
    æ©Ħ
    -0.09
    å¿ĥå¢ĥ
    -0.09
     cartesian
    -0.09
    ãģĦãģĨ
    -0.08
    OLS
    -0.08
     Carol
    -0.08
    å±Ĥå±Ĥ
    -0.08
    说
    -0.08
     Bale
    -0.08
    POSITIVE LOGITS
    æºIJæºIJä¸įæĸŃ
    0.11
    åĩºãģ¦ãģıãĤĭ
    0.10
    溢
    0.09
    fol
    0.09
     deb
    0.09
    æ¶Įåħ¥
    0.09
    ìĦ¼
    0.09
    浩
    0.09
    æĥħåł±ãĤĴ
    0.09
    缸è§ģ
    0.09
    Activations Density 0.033%

    No Known Activations