© 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. 8672
    Prev
    Next
    INDEX
    Explanations

    wood and construction materials

    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
    æĹłæ¯Ķ
    -0.09
    çªĿ
    -0.08
    ingly
    -0.08
    åĨĴçĿĢ
    -0.08
    åIJĪ
    -0.08
    é»ı
    -0.08
    è´«
    -0.08
     gens
    -0.08
    mie
    -0.08
    é¾
    -0.08
    POSITIVE LOGITS
    umer
    0.09
    Ñģад
    0.09
     Shake
    0.09
    iets
    0.09
    æ¡¥
    0.09
    ä¸Ģ段
    0.08
    .bridge
    0.08
    ETS
    0.08
    amarin
    0.08
    Ùģتر
    0.08
    Activations Density 0.026%

    No Known Activations