© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9440
    Prev
    Next
    INDEX
    Explanations

    enjoy nature or outdoors

    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
    æ·Ģç²ī
    -0.09
    ä¸ŃåĽ½åĽ½éĻħ
    -0.08
    à¹Ģà¸Ī
    -0.08
    交è°Ī
    -0.08
    åįķä¸Ģ
    -0.08
    è¶ĭ
    -0.08
    æĪ¬
    -0.08
     Survivor
    -0.08
    artner
    -0.08
    大åİħ
    -0.08
    POSITIVE LOGITS
    大èĩªçĦ¶
    0.17
    æĪ·å¤ĸ
    0.16
    éĩİå¤ĸ
    0.15
    山水
    0.14
     outdoors
    0.14
     outdoor
    0.13
    éĩİçĶŁ
    0.13
     wilderness
    0.13
    Outdoor
    0.12
     nature
    0.12
    Activations Density 0.167%

    No Known Activations