© 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. 19961
    Prev
    Next
    INDEX
    Explanations

    masterpiece, phenomenon, smash, gem

    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
    çļĦéĤ£ç§į
    -0.11
    çľĭ好
    -0.10
    ä¸Ģ侧
    -0.09
    åľ¨ç¾İåĽ½
    -0.09
    éºĤ
    -0.09
    å¯ĨéĽĨ
    -0.09
    éĤ£ç§į
    -0.09
    çļĦä¸Ģç§į
    -0.09
    ä¸ĢåĽŀäºĭ
    -0.08
    ÃŃd
    -0.08
    POSITIVE LOGITS
    åĢij
    0.09
    们
    0.09
    -turned
    0.09
    èĪ¬çļĦ
    0.09
    åĬ
    0.09
    ä¹ĭä½ľ
    0.09
    nels
    0.08
    olic
    0.08
     полÑĮз
    0.08
    ymous
    0.08
    Activations Density 0.158%

    No Known Activations