© 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. 52823
    Prev
    Next
    INDEX
    Explanations

    leave / leaving

    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
    ä¸Ģ声
    -0.10
    æģ°
    -0.09
    IBUT
    -0.09
    utto
    -0.09
    ellig
    -0.09
    èĥİ
    -0.08
    sty
    -0.08
     اÙĦÙĨÙģ
    -0.08
    æµģéĢĿ
    -0.08
    å¥ı
    -0.08
    POSITIVE LOGITS
    离å¼Ģ
    0.10
    æľªç»ı
    0.09
    (exc
    0.09
    å¹´åĨħ
    0.09
     chạm
    0.09
    åĨħå¤ĸ
    0.09
     khá»ıi
    0.09
    raud
    0.09
    éĽ¢éĸĭ
    0.08
    ä¸ĢåĪ»
    0.08
    Activations Density 0.042%

    No Known Activations