© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21292
    Prev
    Next
    INDEX
    Explanations

    awards and prizes

    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
    åŀĽ
    -0.12
    åıijå±ķçļĦ
    -0.09
    èıŁ
    -0.08
    stä
    -0.08
    hashCode
    -0.08
    æĭŁ
    -0.08
    ban
    -0.08
    éŀł
    -0.08
    omon
    -0.08
    bot
    -0.08
    POSITIVE LOGITS
    ä¸ĢçŃīå¥ĸ
    0.19
    äºĮçŃīå¥ĸ
    0.18
    å¥ĸ项
    0.18
    å¥ĸ
    0.17
    å¥ĸåĬ±
    0.17
    ä¸īçŃīå¥ĸ
    0.16
    çįİ
    0.16
    èİ·å¥ĸ
    0.15
     prizes
    0.15
    大å¥ĸ
    0.15
    Activations Density 0.084%

    No Known Activations