© 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. 52636
    Prev
    Next
    INDEX
    Explanations

    questions starting with auxiliary verbs

    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
    æīĵåį¡
    -0.11
    ä¸įç®Ĺ
    -0.10
    è¿Ļ两
    -0.09
    è¿Ļä¹Īåģļ
    -0.09
    举åĬ¨
    -0.09
    éħįä¸Ĭ
    -0.09
    ä¸ĸä¸Ĭ
    -0.09
    æĹĮ
    -0.08
    æĪijè§īå¾Ĺ
    -0.08
     yet
    -0.08
    POSITIVE LOGITS
    æĹ¢è¦ģ
    0.10
    æľīçļĦ
    0.09
    alar
    0.09
    lav
    0.09
    æłİ
    0.09
    åĮħ袱
    0.09
    羣çļĦæĺ¯
    0.09
     Rand
    0.09
    åįķä¸Ģ
    0.09
    è¦ģä¹Ī
    0.08
    Activations Density 0.089%

    No Known Activations