© 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. 36203
    Prev
    Next
    INDEX
    Explanations

    racing circuits and tracks

    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
    ä»ĸä»¬åľ¨
    -0.10
    æĨ¨
    -0.09
    avity
    -0.09
    æĪ¿éĹ´éĩĮ
    -0.08
    ä»ĸåľ¨
    -0.08
    Ùħبر
    -0.08
    æĬµè¾¾
    -0.08
    禽
    -0.08
    æĺ¯ä¸Ģ件
    -0.08
    æīĢåľ¨
    -0.08
    POSITIVE LOGITS
    ä¸Ĭæľī
    0.10
    åĨħå¤ĸ
    0.09
    andon
    0.09
    æ¦Ń
    0.09
    æīĢæľīæĿĥ
    0.09
    éĩijæ²Ļ
    0.09
    è°ĪæģĭçĪ±
    0.09
     Wein
    0.09
    åľ°è²Į
    0.09
    ä¸ĬçļĦ
    0.08
    Activations Density 0.166%

    No Known Activations