© 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. 9108
    Prev
    Next
    INDEX
    Explanations

    names and entities

    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
    身为
    -0.10
    ä½ľä¸ºä¸ĢåIJį
    -0.10
    itten
    -0.09
    èĶļ
    -0.09
    wa
    -0.08
    coni
    -0.08
    æ±°
    -0.08
    ä½ľä¸ºä¸Ģ个
    -0.08
    ä¸Ģæĸ¹éĿ¢æĺ¯
    -0.07
    ehr
    -0.07
    POSITIVE LOGITS
    们çļĦ
    0.10
    çĶŁåĬ¨
    0.09
     Cheney
    0.09
    _names
    0.09
    å°ļ
    0.09
    ATIONAL
    0.08
    Names
    0.08
    ry
    0.08
    éĹ´çļĦ
    0.08
    ç¢İçīĩ
    0.08
    Activations Density 0.187%

    No Known Activations