© 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. 7471
    Prev
    Next
    INDEX
    Explanations

    asking why

    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
    æł¼å±Ģ
    -0.09
    çŀ»
    -0.08
    æī¿
    -0.08
     пÑĢедоÑģÑĤавлÑı
    -0.08
     Ink
    -0.08
    pen
    -0.08
    åįĹåĮĹ
    -0.08
    friendly
    -0.08
     sca
    -0.08
    _elapsed
    -0.08
    POSITIVE LOGITS
     reasons
    0.16
    çIJĨçĶ±
    0.16
     why
    0.15
    çļĦçIJĨçĶ±
    0.14
     Reasons
    0.14
    why
    0.13
    éĩįè¦ģåİŁåĽł
    0.12
    为ä»Ģä¹Ī
    0.12
    åİŁåĽłä¹ĭä¸Ģ
    0.12
     reason
    0.12
    Activations Density 0.070%

    No Known Activations