© 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. 21528
    Prev
    Next
    INDEX
    Explanations

    get out of class

    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
    以åīį
    -0.09
    аÑĩ
    -0.08
    ä»İæĿ¥æ²¡æľī
    -0.08
    éģĩåĪ°äºĨ
    -0.08
     previously
    -0.08
    ä»İæľª
    -0.08
    å½ĵæŶ
    -0.08
     PIE
    -0.08
     Last
    -0.08
    å¤ļå¹´åīį
    -0.07
    POSITIVE LOGITS
    å±ĬæŶ
    0.14
    ä¸ĭåij¨
    0.14
    ä¸ĭ次
    0.13
    æĺİå¹´
    0.13
    åĪ°æŶåĢĻ
    0.12
    æĺİ天
    0.12
    å½»åºķ
    0.12
    ä¸ĭä¸Ģ个
    0.12
     tomorrow
    0.11
    ä¸ĭä¸Ģ
    0.11
    Activations Density 0.058%

    No Known Activations