© 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. 8513
    Prev
    Next
    INDEX
    Explanations

    airline pilot

    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
    ening
    -0.11
    erate
    -0.10
    unt
    -0.09
    -Pacific
    -0.09
    çıŀ
    -0.09
    åµĺ
    -0.09
    ãģªãĤĭ
    -0.09
    hausen
    -0.08
    itecture
    -0.08
    ses
    -0.08
    POSITIVE LOGITS
    gun
    0.10
     disasters
    0.09
    级以ä¸Ĭ
    0.09
    impse
    0.09
    ermo
    0.09
    åѦåĪ°
    0.08
    chers
    0.08
    aru
    0.08
    te
    0.08
    å°ıçĻ½
    0.08
    Activations Density 0.015%

    No Known Activations