© 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. 54000
    Prev
    Next
    INDEX
    Explanations

    publication or public

    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
    UTO
    -0.09
    è¶ĭ
    -0.09
    å¤ĸåĽ½
    -0.08
    æµĵæµĵçļĦ
    -0.08
    æµĵåİļ
    -0.08
     busy
    -0.08
    è¿ĵ
    -0.08
    æĥ³åĪ°äºĨ
    -0.08
    è¿Ħä»Ĭ
    -0.08
    æĪijåıªæĺ¯
    -0.08
    POSITIVE LOGITS
    åħ¬ç¤º
    0.19
    åħ¬åijĬ
    0.18
    åħ¬å¼Ģ
    0.17
    åħ¬å¼Ģåıij
    0.17
    åIJij社ä¼ļ
    0.16
    æĬ¥çº¸
    0.15
    åħ¬å¸ĥ
    0.15
     publicly
    0.13
    åħ¬ä¼Ĺ
    0.13
    åħ¬éĸĭ
    0.13
    Activations Density 0.124%

    No Known Activations