© 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. 11459
    Prev
    Next
    INDEX
    Explanations

    GNU General Public License

    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
    计åĪĴçĶŁèĤ²
    -0.10
    fans
    -0.09
    ega
    -0.09
    éĢļè¡Įè¯ģ
    -0.09
     Rath
    -0.09
    天é¹ħ
    -0.09
    ASE
    -0.08
    éĤ£æł·çļĦ
    -0.08
    æĬĬèĩªå·±çļĦ
    -0.08
    åı¯æĥ³
    -0.08
    POSITIVE LOGITS
    éĤ£å°±æĺ¯
    0.10
    æIJŃ
    0.09
    .SP
    0.08
    Ñĩи
    0.08
    éĻĦ件
    0.08
    æ±Ĺ
    0.08
    汶
    0.08
     Ñģли
    0.08
    åĩºä¼ļ
    0.08
    ijn
    0.08
    Activations Density 0.068%

    No Known Activations