© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19386
    Prev
    Next
    INDEX
    Explanations

    film and business producers

    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
    临æŶ
    -0.10
    姿
    -0.10
     conver
    -0.09
    alytics
    -0.09
    retty
    -0.09
    andon
    -0.09
    深度
    -0.09
    staff
    -0.09
    ias
    -0.08
    weg
    -0.08
    POSITIVE LOGITS
    订éĺħ
    0.11
    åķĨä¸ļåĮĸ
    0.10
    æĢªçī©
    0.10
    æĪIJåIJį
    0.09
    æĤŃ
    0.09
    çĶ¨äººåįķä½į
    0.09
    éĺ´
    0.09
    éĻ°
    0.09
    ç½²
    0.09
     financing
    0.09
    Activations Density 0.137%

    No Known Activations