© 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. 8647
    Prev
    Next
    INDEX
    Explanations

    pad, ack, imes, ler, ico, atch

    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
     bÃło
    -0.09
    æĮ½åĽŀ
    -0.08
    Austin
    -0.08
    estar
    -0.08
    ä¹±
    -0.08
    ä»°
    -0.08
    PARTMENT
    -0.08
    çī
    -0.08
    åĢį
    -0.08
    èģĮèĥ½éĥ¨éŨ
    -0.08
    POSITIVE LOGITS
    bian
    0.09
    алÑĮ
    0.09
    æī©å®¹
    0.08
    exual
    0.08
    APON
    0.08
    å®Įæķ´çļĦ
    0.08
    åĬłè½½
    0.08
    é«ĺéĵģ
    0.08
    æ»ļåĬ¨
    0.08
    å±Ģéĥ¨
    0.08
    Activations Density 0.001%

    No Known Activations