© 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. 20421
    Prev
    Next
    INDEX
    Explanations

    oncogenesis

    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
    âĩ¨
    -0.10
    伤
    -0.09
    locker
    -0.09
     Podesta
    -0.09
    éħį
    -0.09
    iÄħ
    -0.09
    ATAR
    -0.09
     Inject
    -0.09
    éĶ
    -0.09
    æīĵåĮħ
    -0.08
    POSITIVE LOGITS
    éĢį
    0.09
    èį·
    0.09
    ä¼ģä¸ļ管çIJĨ
    0.09
    é«ĺå°ļ
    0.09
    æĸĹ
    0.09
    çIJĨå·¥
    0.09
    ulet
    0.08
    è´²
    0.08
    Chan
    0.08
    åıijçĶŁçļĦ
    0.08
    Activations Density 0.740%

    No Known Activations