© 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. 36550
    Prev
    Next
    INDEX
    Explanations

    action to, moment of, to devote, from plan

    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
    å£ij
    -0.10
    ãģĬé¡ĺãģĦ
    -0.10
     tá
    -0.09
    æĪijæĬĬ
    -0.09
     Scrolls
    -0.09
    åĮħ袱
    -0.09
    imas
    -0.09
    åı¦æľī
    -0.09
    ç¼£
    -0.09
    殿ä¸ĭ
    -0.09
    POSITIVE LOGITS
    æļĤåģľ
    0.10
    åģľä¸ĭæĿ¥
    0.10
    ä¼ijåģĩ
    0.10
    åģľä¸ĭ
    0.10
    æĶĴ
    0.09
    æīĢèĥ½
    0.09
    为大家
    0.09
    pond
    0.09
    æŃ£è§Ħ
    0.09
    æĶ¾ä¸ĭ
    0.09
    Activations Density 0.035%

    No Known Activations