© 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. 61065
    Prev
    Next
    INDEX
    Explanations

    expressing desire

    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
    éĩįç£ħ
    -0.09
     ÑĩаÑģÑĤо
    -0.08
    ģı
    -0.08
    ä»·åĢ¼
    -0.08
    rov
    -0.08
    åij¨å¹´
    -0.08
    åħīçݯ
    -0.08
    大å®Ĺ
    -0.08
    æľ¬è´¨ä¸Ĭ
    -0.08
    Enumerator
    -0.07
    POSITIVE LOGITS
    ä½ļ
    0.12
    æľīæľºä¼ļ
    0.10
    åľ°çľĭçĿĢ
    0.10
     (?)
    0.10
    å¾ķ
    0.09
    è¦ģåģļ好
    0.09
    åIJ¬åIJ¬
    0.09
    ulously
    0.09
    äºĨåįĬ天
    0.09
    æĹ©æĹ¥
    0.09
    Activations Density 0.005%

    No Known Activations