© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 57620
    Prev
    Next
    INDEX
    Explanations

    company founder

    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
    让å®ĥ
    -0.11
    öt
    -0.10
    GIN
    -0.10
    åºľ
    -0.09
     меÑĢ
    -0.09
    _Collections
    -0.08
    agrams
    -0.08
    ippy
    -0.08
    	types
    -0.08
    ubs
    -0.08
    POSITIVE LOGITS
    èĢħ
    0.17
    èĢħçļĦ
    0.17
    人åijĺ
    0.15
    èĢħãģ¯
    0.15
    å·¥ä½ľèĢħ
    0.14
    人士
    0.14
    人åĵ¡
    0.14
    èĢħãģĮ
    0.14
    ä»İä¸ļèĢħ
    0.13
    è¿ĻäºĽäºº
    0.12
    Activations Density 0.811%

    No Known Activations