© 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. 9180
    Prev
    Next
    INDEX
    Explanations

    date formatting and manipulation

    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
    åĩºè·¯
    -0.08
    åĩºåĵģ
    -0.08
    çijķ
    -0.08
    åij¨æľ«
    -0.08
    å¼Ĥ
    -0.08
    ×ķ×ŀ×Ķ
    -0.08
    .IO
    -0.08
    交æµģ
    -0.08
    线ä¸Ĭ线ä¸ĭ
    -0.08
    áĥij
    -0.08
    POSITIVE LOGITS
    .getMonth
    0.10
    驯
    0.09
     calendar
    0.09
    umper
    0.09
    -picker
    0.09
    .month
    0.09
    ToStr
    0.09
    ëł¥
    0.09
    .strptime
    0.09
    Picker
    0.09
    Activations Density 0.461%

    No Known Activations