© 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. 9425
    Prev
    Next
    INDEX
    Explanations

    sponsored by

    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
    éĿĽ
    -0.09
    çł´
    -0.09
    7
    -0.08
    8
    -0.08
    åī§ä¸Ń
    -0.08
    exc
    -0.08
    9
    -0.08
    æ£ł
    -0.08
    lett
    -0.08
    åĿĬ
    -0.08
    POSITIVE LOGITS
    PRI
    0.10
    CodeAt
    0.09
    åı¯ä»¥æĽ´å¥½
    0.09
    åıī
    0.08
    .Scan
    0.08
    éħįåIJĪ
    0.08
    enville
    0.08
    éĤªæģ¶
    0.08
    æľº
    0.08
    ennie
    0.08
    Activations Density 0.016%

    No Known Activations