© 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. 18389
    Prev
    Next
    INDEX
    Explanations

    continues to permit, allows, aims for

    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¥ī
    -0.08
    æ¯ĶæĭŁ
    -0.08
    acre
    -0.08
    ç©·
    -0.07
    æĮ¯ãĤĬ
    -0.07
    åıijçİ°
    -0.07
    漫
    -0.07
    ги
    -0.07
     Princip
    -0.07
     Affero
    -0.07
    POSITIVE LOGITS
    请éĹ®
    0.10
    被è§Ĩ为
    0.09
    æ·Į
    0.09
    åħħ满äºĨ
    0.09
    æ²¥
    0.09
    审
    0.09
    亲çĪ±
    0.09
    éŀĺ
    0.09
    幸è¿IJ
    0.09
    .wh
    0.09
    Activations Density 1.509%

    No Known Activations