© 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. 51545
    Prev
    Next
    INDEX
    Explanations

    artifact detection

    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
    opro
    -0.11
    æľĢåŁºæľ¬
    -0.10
    æĸ¹å¼ıè¿Ľè¡Į
    -0.09
    Acceler
    -0.09
    /Product
    -0.09
    æ½ľ
    -0.09
    æķ²
    -0.08
    lamp
    -0.08
    æ°¸ä¹ħ
    -0.08
    çľĭä¸įæĩĤ
    -0.08
    POSITIVE LOGITS
    æķĪæŀľ
    0.09
    åĴĦ
    0.08
     arte
    0.08
    æµ´
    0.08
    æīĢå¾Ĺ
    0.08
    é¦Ĭ
    0.08
     artifact
    0.08
    åİĭæĬij
    0.08
    witter
    0.08
    æŃ£ç¡®çļĦ
    0.08
    Activations Density 0.497%

    No Known Activations