© 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. 20075
    Prev
    Next
    INDEX
    Explanations

    units of measurement

    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
     коÑĤоÑĢÑĭÑħ
    -0.09
    angers
    -0.09
    å°ij许
    -0.09
    оÑĢÑĤ
    -0.09
    ç»ıå¼Ģ
    -0.09
    acular
    -0.08
    ä¼ļè§īå¾Ĺ
    -0.08
     Cathy
    -0.08
    sse
    -0.08
    ç¨į
    -0.08
    POSITIVE LOGITS
    讽
    0.11
    åįİå°Ķ
    0.10
    èĢĮä¸Ķ
    0.09
    UTO
    0.09
    åİŁèijĹ
    0.08
    åıĹåĪ°äºĨ
    0.08
     Äij
    0.08
    ä¸Ģ楼
    0.08
    .construct
    0.08
    éĿŀ常çļĦ
    0.08
    Activations Density 0.528%

    No Known Activations