© 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. 9595
    Prev
    Next
    INDEX
    Explanations

    more than, less than, as ... as

    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
    对èĩªå·±
    -0.10
    æĬ¤çħ§
    -0.09
    avo
    -0.09
     اÙĦسÙĨ
    -0.09
    ute
    -0.09
    è°ģçŁ¥éģĵ
    -0.09
    è£ī
    -0.08
    å®ŀäºĭ
    -0.08
    éĹ®éĹ®
    -0.08
    æ®ĩ
    -0.08
    POSITIVE LOGITS
    éĢ¼
    0.10
    acons
    0.09
    é¼ĵ
    0.09
    iki
    0.08
    åĭī
    0.08
    ç«Ń
    0.08
    Young
    0.08
    éļ¾
    0.08
    æ¶Į
    0.08
    PHA
    0.08
    Activations Density 0.034%

    No Known Activations