© 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. 9238
    Prev
    Next
    INDEX
    Explanations

    imagined designs and art direction

    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
    estone
    -0.09
    å°ıçĻ½
    -0.09
     resta
    -0.09
    etag
    -0.09
    æĭĬ
    -0.08
    æij½
    -0.08
    URN
    -0.08
    cling
    -0.08
     Licensed
    -0.08
    Manufact
    -0.08
    POSITIVE LOGITS
    å½¢æĢģ
    0.09
     диз
    0.08
    åĢŁéī´
    0.08
    طر
    0.08
    éĺĶ
    0.08
    çİĭåĽ½
    0.08
    æŀĦ
    0.08
    æīŃæĽ²
    0.08
    .sess
    0.08
    åħµåĻ¨
    0.08
    Activations Density 0.110%

    No Known Activations