© 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. 10053
    Prev
    Next
    INDEX
    Explanations

    emerge or come out on top

    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
    é²
    -0.10
    æĸ°ä¸ī
    -0.10
    raud
    -0.09
     Engel
    -0.09
    就好åĥı
    -0.09
    éĮĦ
    -0.08
    ipel
    -0.08
    å¼ĢæĿ¥
    -0.08
    æĿŀ
    -0.08
    就好
    -0.08
    POSITIVE LOGITS
    ä¸įåıĺ
    0.11
    èĥľåĪ©
    0.10
    gles
    0.09
    дол
    0.09
     victorious
    0.08
    æľĢç»Ī
    0.08
    .getBean
    0.08
    .ie
    0.08
     Orb
    0.08
    çķ¥æľī
    0.08
    Activations Density 0.015%

    No Known Activations