© 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. 50568
    Prev
    Next
    INDEX
    Explanations

    rates

    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
    顶
    -0.09
    æijĨ
    -0.09
    檫
    -0.08
    è¹ī
    -0.08
    ä¸ķ
    -0.08
    ç¦ģ
    -0.08
    éĩĬ
    -0.08
    æľīä»·åĢ¼
    -0.08
    æ¾Ħæ¸ħ
    -0.08
    éłĤ
    -0.08
    POSITIVE LOGITS
     rates
    0.16
    ç¨İçİĩ
    0.15
     rate
    0.14
    è´¹çİĩ
    0.13
    åĪ©çİĩ
    0.13
    .rate
    0.13
    rates
    0.13
    rate
    0.12
     Rates
    0.12
    Rates
    0.12
    Activations Density 0.045%

    No Known Activations