© 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. 38365
    Prev
    Next
    INDEX
    Explanations

    if you

    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
    å¿ĥ缮
    -0.09
     дог
    -0.09
    æĥŃ
    -0.09
    çŀĢ
    -0.09
    ãĤĭãģŁãĤģãģ«
    -0.08
    å·²äºİ
    -0.08
    Spoiler
    -0.08
    å¦Ĥæŀľæľī
    -0.08
    æĪij们åºĶ该
    -0.08
    ApplicationContext
    -0.08
    POSITIVE LOGITS
    å°±èĥ½
    0.11
    åĨįåĬłä¸Ĭ
    0.11
    åĨįå¤ļ
    0.10
    çļĦè¯Ŀ
    0.10
    ä¹Łèĥ½
    0.09
    å¾Ĺ好
    0.09
    éĥ½èĥ½
    0.09
    åĨįçĶŁ
    0.09
    便åı¯
    0.09
    å°±åı¯ä»¥
    0.09
    Activations Density 0.128%

    No Known Activations