© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 20918
    Prev
    Next
    INDEX
    Explanations

    Christian followed by name or descriptive term

    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
    å¾Ĺèµ·
    -0.11
    inding
    -0.10
    æĤ´
    -0.09
    dated
    -0.09
    主ä¸ļ
    -0.09
    ithe
    -0.09
    chie
    -0.09
    累累
    -0.09
    bidden
    -0.09
    åķ¬
    -0.09
    POSITIVE LOGITS
    ../../../
    0.10
    o
    0.10
    isme
    0.10
    uzzi
    0.10
    -Muslim
    0.09
    ly
    0.09
    íıIJ
    0.09
    ität
    0.09
    ç͍åĵģ
    0.09
    like
    0.09
    Activations Density 0.018%

    No Known Activations