© 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. 9548
    Prev
    Next
    INDEX
    Explanations

    robust systems and business

    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
    er
    -0.08
    ÙĪÙĩا
    -0.08
     OSI
    -0.08
    çī¢åĽºæłijç«ĭ
    -0.08
     tern
    -0.08
    vers
    -0.08
    妤
    -0.08
    icion
    -0.08
    tran
    -0.08
    igraph
    -0.08
    POSITIVE LOGITS
    ness
    0.20
    ly
    0.12
    NESS
    0.12
    èĢIJçĶ¨
    0.12
    æĢ§å¼º
    0.10
    ä¸İåIJ¦
    0.10
    ively
    0.09
    htable
    0.09
    nya
    0.09
    iveness
    0.09
    Activations Density 0.008%

    No Known Activations