© 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. 19404
    Prev
    Next
    INDEX
    Explanations

    climate change and warming

    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
     нев
    -0.10
    åıĹçģ¾
    -0.09
    ä¸įæĪIJ
    -0.09
    lake
    -0.08
    严峻
    -0.08
    odem
    -0.08
    çłĶ
    -0.08
     embr
    -0.08
    è¡Ģç³ĸ
    -0.08
    ç½ijæĬķ
    -0.08
    POSITIVE LOGITS
    çݰ代社ä¼ļ
    0.09
    æ²¥
    0.09
    arger
    0.09
    è¡ĮæĶ¿å®¡æī¹
    0.09
    é©¿
    0.08
    骥
    0.08
    .retry
    0.08
    æ±ī
    0.08
    称ä¹ĭ
    0.08
    æĵİ
    0.08
    Activations Density 0.027%

    No Known Activations