© 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. 58514
    Prev
    Next
    INDEX
    Explanations

    neither ... not

    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
    大æ´ĭ
    -0.10
    好ä¸į容æĺĵ
    -0.10
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.10
    æĶ¹æĪIJ
    -0.10
    å¤ļäºĨ
    -0.09
    æľ¬çĿĢ
    -0.09
    å®ļäºĨ
    -0.09
    æł©
    -0.09
    ä¸Ģç§į
    -0.09
    éĿŀ常å¤ļçļĦ
    -0.09
    POSITIVE LOGITS
     neither
    0.17
    ä¸įèĥ½
    0.17
    ä¸įåľ¨
    0.16
    并没æľī
    0.15
    就没æľī
    0.15
     Neither
    0.15
    æĹłæ³ķ
    0.15
    å¹¶æľª
    0.15
    ä¹Łæ²¡æľī
    0.14
    ä¸įåħ·å¤ĩ
    0.14
    Activations Density 0.367%

    No Known Activations