© 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. 7694
    Prev
    Next
    INDEX
    Explanations

    pressing or press variations

    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
    aji
    -0.09
    èĩªä¿¡
    -0.09
    idad
    -0.09
    宥
    -0.09
    .mag
    -0.09
    ç½´
    -0.08
    泡泡
    -0.08
     Aires
    -0.08
    磨
    -0.08
     forms
    -0.08
    POSITIVE LOGITS
     pressed
    0.10
     pressing
    0.10
    æļĤåģľ
    0.10
    ures
    0.10
    .press
    0.09
    anan
    0.09
    ãĦ
    0.09
    Pressed
    0.08
     Press
    0.08
     Farr
    0.08
    Activations Density 0.024%

    No Known Activations