© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8579
    Prev
    Next
    INDEX
    Explanations

    came in second

    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
    emies
    -0.09
    çķĻåѦ
    -0.09
    åIJĮå¿Ĺ们
    -0.09
    æŃ£ä¹ī
    -0.09
    .ylim
    -0.09
     Ñģоб
    -0.09
    åĨħ饰
    -0.09
    èµ·æĿ¥äºĨ
    -0.09
    åīįç½®
    -0.08
    insula
    -0.08
    POSITIVE LOGITS
    éĽħ
    0.10
    æĵ¦
    0.08
    ray
    0.08
    utt
    0.08
     Barton
    0.08
    æİ¥åľ°
    0.08
    å¯Į
    0.08
     Arn
    0.08
    æĪŁ
    0.08
    (argument
    0.08
    Activations Density 0.009%

    No Known Activations