© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7891
    Prev
    Next
    INDEX
    Explanations

    positive sentiments about support

    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
    ÑĭÑĪ
    -0.11
     buck
    -0.09
    ereg
    -0.09
    æįı
    -0.09
    èģĮä¸ļæĬĢèĥ½
    -0.08
    å¼ĤæĢ§
    -0.08
    isOk
    -0.08
    avia
    -0.08
    åĭĭ
    -0.08
    è§Ĥ
    -0.08
    POSITIVE LOGITS
    ç»ĻäºĨæĪij
    0.18
    使æĪij
    0.16
    帮æĪij
    0.15
    ãģ£ãģ¦ãģıãĤĮ
    0.15
    ç»ĻæĪij
    0.14
    让æĪij
    0.14
    ãģĹãģ¦ãģıãĤĮ
    0.13
    åĮħ容
    0.13
    æĪijå¾Ī
    0.12
    æĬĬæĪij
    0.12
    Activations Density 0.088%

    No Known Activations