© 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. 36617
    Prev
    Next
    INDEX
    Explanations

    win or earn achievements

    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
    åŨ
    -0.09
    пÑĥÑģÑĤ
    -0.09
    é©°
    -0.09
    ç«ĭãģ¦
    -0.09
    æ¶ij
    -0.09
    åºIJ
    -0.08
    æīĵå¾Ĺ
    -0.08
    ä¸Ń举
    -0.08
    esk
    -0.08
     tiá»ĩn
    -0.08
    POSITIVE LOGITS
    ä¿¡ä»»
    0.12
    å°Ĭéĩį
    0.11
    çIJĨ解åĴĮ
    0.10
    лаÑģÑĤ
    0.10
    éĿĴçĿIJ
    0.10
    çļĦçIJĨ解
    0.09
     ever
    0.09
    _fr
    0.09
    çIJĨ解
    0.09
    rum
    0.08
    Activations Density 0.031%

    No Known Activations