© 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. 39024
    Prev
    Next
    INDEX
    Explanations

    would you like to know

    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
    éĤ£åıª
    -0.09
    ÑģÑĤÑĢÑĥк
    -0.09
    æĥ³äºĨ
    -0.08
     Hogan
    -0.08
    èĶ½
    -0.08
    éĽ¾
    -0.08
    orris
    -0.08
    å¾Īæ¸ħæ¥ļ
    -0.08
    äºĽ
    -0.08
    ä»»
    -0.08
    POSITIVE LOGITS
    å¿«æĬ¥
    0.10
    оÑī
    0.10
    é¦Ĵ头
    0.10
    æĿ¥å½¢å®¹
    0.10
    ä¼ī
    0.10
    yyy
    0.09
    rons
    0.09
    亿ä¸ĩ
    0.09
    æĺ¯éŁ©åĽ½
    0.09
    èĤ²
    0.09
    Activations Density 0.028%

    No Known Activations