© 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. 33747
    Prev
    Next
    INDEX
    Explanations

    , the

    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
    第äºĮ大
    -0.10
    çļĦå°±æĺ¯
    -0.09
     boss
    -0.09
    äºĶæĺŁ
    -0.09
    缤
    -0.09
    é«Ģ
    -0.08
    æīĢ以æĪij
    -0.08
    éĥ½æĺ¯éĿŀ常
    -0.08
    boss
    -0.08
    è¶Ĭ
    -0.08
    POSITIVE LOGITS
    że
    0.08
    alom
    0.08
    说å®Į
    0.08
    ç»Ī端
    0.08
    omon
    0.08
    å½ĵä¸ĭ
    0.08
    iform
    0.08
    æľ«ç«¯
    0.08
    èĥ¡åIJĮ
    0.08
     tcp
    0.08
    Activations Density 0.178%

    No Known Activations