© 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. 27772
    Prev
    Next
    INDEX
    Explanations

    success and accomplishment

    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
    æĪIJ交
    -0.10
    çĥŃéĹ¹
    -0.09
    åľī
    -0.08
    ä¸įæ¸ħ
    -0.08
    æ¡ĮåŃIJ
    -0.08
    å¾Īæ£Ĵ
    -0.08
    äºĶæĺŁ
    -0.08
    å¹»
    -0.08
     successful
    -0.08
    é»Ħæĺı
    -0.08
    POSITIVE LOGITS
    arro
    0.10
    çļĦåĨ³å¿ĥ
    0.09
    óst
    0.09
    оÑģÑĤоÑı
    0.09
     Sap
    0.09
    fully
    0.09
    -minded
    0.09
    ÙħÙĬÙĨ
    0.09
    VML
    0.08
    æ¯ıä¸Ģ天
    0.08
    Activations Density 0.038%

    No Known Activations