© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 54147
    Prev
    Next
    INDEX
    Explanations

    has to do with

    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
     Dial
    -0.09
    åľ°ä¸Ĭ
    -0.09
    对æѤ
    -0.09
    æĬľ
    -0.09
     dial
    -0.09
    åºĶæľīçļĦ
    -0.09
    çĶ¨éĩı
    -0.08
    æĭ¨
    -0.08
    太太
    -0.08
    Forge
    -0.08
    POSITIVE LOGITS
    æ¶īåıĬåĪ°
    0.17
    æ¶īåıĬ
    0.17
     involving
    0.12
     ÙĬتعÙĦÙĤ
    0.12
     involve
    0.12
     involves
    0.12
    تعÙĦÙĤ
    0.11
    两级
    0.10
    æ¶ī
    0.10
    åŁºäºİ
    0.09
    Activations Density 0.191%

    No Known Activations