© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 39379
    Prev
    Next
    INDEX
    Explanations

    monthly cycle, period, or billing

    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
    ä¸ī人
    -0.10
    两人
    -0.10
    æ°ijçĶŁ
    -0.09
    äºĮ人
    -0.08
    -fetch
    -0.08
    ref
    -0.08
    æIJŃ
    -0.08
    åĪ·
    -0.08
    åīĸ
    -0.08
    Years
    -0.08
    POSITIVE LOGITS
    æľĪåĪĿ
    0.18
    æľĪæľ«
    0.16
    æľĪåºķ
    0.16
    æľĪä¸Ń
    0.14
    æľ¬æľĪ
    0.12
     monthly
    0.11
    æľĪç»ı
    0.11
     month
    0.11
    æ¯ıæľĪ
    0.11
    姨
    0.10
    Activations Density 0.112%

    No Known Activations