© 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. 51243
    Prev
    Next
    INDEX
    Explanations

    birthday, anniversary, year

    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
    çķ¥
    -0.09
    对å¾ħ
    -0.09
    æĽĻ
    -0.09
    çķĻä½ı
    -0.09
    èĢĮåĩº
    -0.09
    çľĭå¾ħ
    -0.09
     Jak
    -0.08
    abox
    -0.08
    å°ijæķ°
    -0.08
    æĮ¤
    -0.08
    POSITIVE LOGITS
    åij¨å¹´
    0.12
     anniversary
    0.10
    hl
    0.09
    æĪį
    0.09
    ITICAL
    0.08
    纪念
    0.08
    .Operation
    0.08
    åħħå®ŀ
    0.08
    年纪
    0.08
    ä¸ģ
    0.08
    Activations Density 0.058%

    No Known Activations