© 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. 20856
    Prev
    Next
    INDEX
    Explanations

    architecture and associated concepts

    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
    åĮ»åĬ¡äººåijĺ
    -0.10
    åĨľå®¶
    -0.10
     обоÑĢ
    -0.09
    æŁ¥èİ·
    -0.09
    èį¯çī©
    -0.08
    交åıĭ
    -0.08
    çķ
    -0.08
    acco
    -0.08
    á»ijc
    -0.08
    ä¸įçĽ¸ä¿¡
    -0.08
    POSITIVE LOGITS
    建çŃijå¸Ī
    0.20
    建çŃij
    0.19
    建ç¯ī
    0.15
     Architect
    0.15
     architectural
    0.14
    建éĢł
    0.14
     Buildings
    0.14
    建çŃij设计
    0.13
    设计å¸Ī
    0.13
    ç«ĭéĿ¢
    0.13
    Activations Density 0.165%

    No Known Activations