© 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. 20526
    Prev
    Next
    INDEX
    Explanations

    simple or complicated

    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
    æĽ´æľī
    -0.10
    æĦŁè§¦
    -0.09
    ynch
    -0.09
    æĺ¯æľī
    -0.09
    jax
    -0.08
    æ»Ķ
    -0.08
    몰
    -0.08
    åĻ¤
    -0.08
    æģ£
    -0.08
    utex
    -0.08
    POSITIVE LOGITS
    ç®Ģåįķ
    0.14
    å°±è¿Ļä¹Ī
    0.14
    ç®ĢåįķçļĦ
    0.14
    å¾Īç®Ģåįķ
    0.13
     simple
    0.13
    éĤ£ä¹Īç®Ģåįķ
    0.12
    ç°¡åĸ®
    0.12
    æ¯Ķè¾ĥç®Ģåįķ
    0.12
    ãĤ·ãĥ³ãĥĹãĥ«
    0.12
     simplicity
    0.12
    Activations Density 0.068%

    No Known Activations