© 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. 52645
    Prev
    Next
    INDEX
    Explanations

    relationship or connection

    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
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.12
    UnderTest
    -0.10
    erras
    -0.10
    ä¸ī个æĸ¹éĿ¢
    -0.09
     Sark
    -0.09
    å·¡åĽŀ
    -0.09
    åħļçļĦé¢Ĩ导
    -0.09
    ä¹Łæĺ¯ä¸Ģç§į
    -0.09
     surprisingly
    -0.08
    çĭ¬çī¹
    -0.08
    POSITIVE LOGITS
    ä½Ĩ对äºİ
    0.12
    çļĦä¼łç»Ł
    0.11
    çĶ¨åĬĽ
    0.11
    åı¯ä»¥çĽ´æİ¥
    0.10
    éĿĻæĢģ
    0.10
    éĽī
    0.10
    ä¼łç»Ł
    0.10
    ä½Ĩæĺ¯å¯¹äºİ
    0.09
    è½°
    0.09
    åĽºçĦ¶
    0.09
    Activations Density 1.216%

    No Known Activations