© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38147
    Prev
    Next
    INDEX
    Explanations

    application form

    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
    icz
    -0.09
    orted
    -0.09
    _lift
    -0.08
    é¢Ĺç²Ĵ
    -0.08
    æŀ¯
    -0.08
    inus
    -0.08
    éģĹæĨ¾
    -0.08
    ited
    -0.08
     Arabian
    -0.08
    æĥ¯ä¾ĭ
    -0.08
    POSITIVE LOGITS
    被çĽĹ
    0.10
    é¦ĸåħĪæĺ¯
    0.09
    аниз
    0.09
    ento
    0.08
     Bair
    0.08
    æĿ¥èĩª
    0.08
    åĮĻ
    0.08
    enta
    0.08
    uden
    0.08
    ä¸Ĭæľī
    0.08
    Activations Density 0.017%

    No Known Activations