© 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. 51561
    Prev
    Next
    INDEX
    Explanations

    swearing and language

    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
     WebDriverWait
    -0.09
    åĪĢ
    -0.09
    涮
    -0.09
     мÑıг
    -0.08
    çī¹æ´¾
    -0.08
    澡
    -0.08
    prises
    -0.08
    uments
    -0.08
    亲å¯Ĩ
    -0.08
    nos
    -0.08
    POSITIVE LOGITS
    oola
    0.10
    亨
    0.09
    ewan
    0.09
    lemn
    0.09
    Reality
    0.09
    dest
    0.09
    çļĦåŁİå¸Ĥ
    0.08
    åĶ¤
    0.08
    ç½ķ
    0.08
    åĽ½åľŁèµĦæºIJ
    0.08
    Activations Density 0.008%

    No Known Activations