© 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. 37023
    Prev
    Next
    INDEX
    Explanations

    a `a` `an` `another` `your`

    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
    æ¡Ĩ
    -0.09
    æīĭä¸ŃçļĦ
    -0.09
    jo
    -0.08
    åľ¨è¿Ļ个
    -0.08
    Agency
    -0.08
     pageNumber
    -0.08
    è§Ĭ
    -0.08
    åĵªæĢķæĺ¯
    -0.08
    aign
    -0.08
     Agency
    -0.08
    POSITIVE LOGITS
    oftware
    0.10
    anced
    0.09
    PELL
    0.09
    é«ĺä¸ī
    0.09
    ounds
    0.09
    PILE
    0.09
    _deposit
    0.09
    à¹Ĥล
    0.09
    äºĨä¸Ģ声
    0.09
    éĴĬ
    0.09
    Activations Density 0.045%

    No Known Activations