© 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. 51865
    Prev
    Next
    INDEX
    Explanations

    attached image or screenshot

    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
    罡
    -0.10
    çĶŃ
    -0.09
    oux
    -0.09
    mony
    -0.09
    çIJ®
    -0.09
    orra
    -0.08
    繪
    -0.08
    ãģĤãĤĬãģĮãģ¨ãģĨãģĶãģĸãģĦãģ¾ãģĹãģŁ
    -0.08
    篱
    -0.08
    éĩı
    -0.08
    POSITIVE LOGITS
     below
    0.14
     ниже
    0.14
     above
    0.13
    below
    0.13
    æīĢ示
    0.12
    ictured
    0.12
    ä¸ĭéĿ¢
    0.12
     abaixo
    0.11
    åĽ¾ä¸º
    0.11
     вÑĭÑĪе
    0.11
    Activations Density 0.102%

    No Known Activations