© 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. 35991
    Prev
    Next
    INDEX
    Explanations

    explore the

    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
    æłī
    -0.09
    æĢµ
    -0.09
    å°¼æĸ¯
    -0.09
    赶æĿ¥
    -0.09
     Disp
    -0.08
     ìĪľê°Ħ
    -0.08
    anny
    -0.08
    èĪĮ头
    -0.08
    èĥ½çľĭåĩº
    -0.08
    ä¸ĬæĿ¥
    -0.08
    POSITIVE LOGITS
    æŀģèĩ´
    0.13
     вопÑĢоÑģ
    0.10
     themes
    0.10
    æ·±å±Ĥ次
    0.10
    æĪIJ为ä¸ĢåIJį
    0.09
    æݾ
    0.09
     далÑĮÑĪе
    0.09
    让å®ĥ
    0.09
    æ·±å±Ĥ
    0.09
     avenues
    0.09
    Activations Density 0.078%

    No Known Activations