© 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. 37350
    Prev
    Next
    INDEX
    Explanations

    returned queries or actions

    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
    trak
    -0.09
    aret
    -0.09
    并ä¸İ
    -0.09
    hire
    -0.09
    ddl
    -0.08
    æĭŃ
    -0.08
    娩
    -0.08
     amen
    -0.08
    hoa
    -0.08
    åŀ©
    -0.08
    POSITIVE LOGITS
    æľ¬èº«å°±
    0.10
    mund
    0.09
    çļĦ带é¢Ĩ
    0.09
    ä¸Ĭæ¼Ķ
    0.09
    sched
    0.08
    .Annotations
    0.08
    好好
    0.08
    ouncy
    0.08
    _CONFIRM
    0.08
    ).__
    0.08
    Activations Density 0.008%

    No Known Activations