© 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. 39108
    Prev
    Next
    INDEX
    Explanations

    happened already

    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
    åıĪ好
    -0.11
    rü
    -0.09
    ä¸įåİ»
    -0.09
    åīįä¸ĸ
    -0.09
    permit
    -0.09
    ermen
    -0.09
    inium
    -0.09
    å®
    -0.09
    æĭĪ
    -0.08
    篪
    -0.08
    POSITIVE LOGITS
     already
    0.20
     Already
    0.18
    å·²ç»ıå¼Ģå§ĭ
    0.18
    å·²ç»ıåľ¨
    0.18
    already
    0.18
    å·²ç»ıæľī
    0.18
    Already
    0.17
     Ñĥже
    0.17
    å·²æľī
    0.17
    å·²ç»ıæĺ¯
    0.16
    Activations Density 0.054%

    No Known Activations