© 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. 19007
    Prev
    Next
    INDEX
    Explanations

    after a period or event

    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
    èĩªä»İ
    -0.10
    åħ¶å®ŀæĺ¯
    -0.10
    äºĨèµ·æĿ¥
    -0.10
    åĪ°æŶåĢĻ
    -0.10
    åIJİæľŁ
    -0.10
    èµ·æĿ¥äºĨ
    -0.09
    å¾ĪæŃ£å¸¸
    -0.09
    aan
    -0.09
    åĨįä¹Ł
    -0.09
    ãģĦãģĭ
    -0.09
    POSITIVE LOGITS
    ward
    0.13
    wards
    0.11
    å¤ļå¹´çļĦ
    0.11
    noon
    0.10
    WARDS
    0.09
    ä¸Ģçķª
    0.09
    oretical
    0.09
    两年
    0.08
    ä¼Ĺå¤ļ
    0.08
    quoi
    0.08
    Activations Density 0.048%

    No Known Activations