© 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. 36843
    Prev
    Next
    INDEX
    Explanations

    disclosure and risks

    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
    åĿIJä¸ĭ
    -0.09
    年代
    -0.09
    æµģè¡Į
    -0.09
    é»ĺå¥ij
    -0.09
     sit
    -0.09
     sat
    -0.08
    åĿIJ
    -0.08
    轶
    -0.08
    çıŀ
    -0.08
    éĢ®
    -0.08
    POSITIVE LOGITS
    æ¸ħæ¥ļ
    0.13
    æĺİçĻ½äºĨ
    0.12
    åĬĿ
    0.12
    èѦåijĬ
    0.11
    æĺİçĻ½
    0.11
    éĥijéĩį
    0.11
    çŁ¥æĻĵ
    0.11
    èŃ¦ç¤º
    0.11
    çŁ¥æĥħ
    0.11
    æĨ¨
    0.11
    Activations Density 0.067%

    No Known Activations