© 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. 3231
    Prev
    Next
    INDEX
    Explanations

    less risk, less time, less farm

    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
    客
    -0.09
    çĽ²
    -0.09
    æĤ¬
    -0.09
    æĽ¾
    -0.09
    åIJįåĪĹ
    -0.09
    å·®çĤ¹
    -0.08
     лÑİбого
    -0.08
     даж
    -0.08
    该éĻ¢
    -0.08
    bard
    -0.07
    POSITIVE LOGITS
    ä¼ļè§īå¾Ĺ
    0.10
    åĬ¿å¿ħ
    0.10
    éħįå¥Ĺ
    0.09
    åıªå¥½
    0.09
    åĽłä¸ºä»ĸ们
    0.09
    åĩºäºİ
    0.09
    çļĦç¼ĺæķħ
    0.09
    æĹ¢çĦ¶
    0.09
    æľ¬æĿ¥å°±
    0.09
    åıĹä¸įäºĨ
    0.09
    Activations Density 0.177%

    No Known Activations