© 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. 52090
    Prev
    Next
    INDEX
    Explanations

    United States Army Government

    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¸ŃåĽ½åĽ½éĻħ
    -0.11
    å®īå±ħ
    -0.09
    orian
    -0.09
    æĪijåĽ½
    -0.09
    æĪijçľģ
    -0.09
    nist
    -0.09
    æĪijéĻ¢
    -0.09
    etal
    -0.08
     mente
    -0.08
    æĹ¶ä»£ä¸ŃåĽ½
    -0.08
    POSITIVE LOGITS
    西åĮĹ
    0.10
    sto
    0.09
     dụng
    0.09
    纷
    0.08
     rar
    0.08
    æħĪæĤ²
    0.08
    æĦł
    0.08
    æħĪ
    0.08
     Cov
    0.08
    åľ¨æѤ
    0.08
    Activations Density 0.111%

    No Known Activations