© 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. 9620
    Prev
    Next
    INDEX
    Explanations

    attached to or into

    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
     Meyer
    -0.09
    å¯ĵæĦı
    -0.09
    bah
    -0.09
    osphere
    -0.09
    activex
    -0.09
     Latest
    -0.09
    æѤ
    -0.09
    æĥ³çĿĢ
    -0.08
    èģĶ
    -0.08
    chal
    -0.08
    POSITIVE LOGITS
    çİ°æľīçļĦ
    0.14
    åİŁæľīçļĦ
    0.13
    åİŁæľī
    0.11
    çİ°æľī
    0.11
     existing
    0.11
    æĻ®éĢļçļĦ
    0.09
    ä¸Ģ个å°ı
    0.09
    çļĦéĤ£ç§į
    0.09
    æĺı
    0.09
     either
    0.09
    Activations Density 0.382%

    No Known Activations